Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Abstract

In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.

Under review as a conference paper at ICLR 2016

References in corpus (7)

• Striving for Simplicity: The All Convolutional Net
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• DRAW: A Recurrent Neural Network For Image Generation
• A note on the evaluation of generative models
• Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
• Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
• Understanding Locally Competitive Networks

Cited by in corpus (1864)

• Transformers in Vision: A Survey
• ICLabel: An automated electroencephalographic independent component classifier, dataset, and website
• Conditional Image Synthesis With Auxiliary Classifier GANs
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Generative Adversarial Network in Medical Imaging: A Review
• Deep Facial Expression Recognition: A Survey
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Unsupervised Representation Learning by Predicting Image Rotations
• Improved Training of Wasserstein GANs
• NIPS 2016 Tutorial: Generative Adversarial Networks
• A guide to convolution arithmetic for deep learning
• Deep Learning for Single Image Super-Resolution: A Brief Review
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• A trans-disciplinary review of deep learning research for water resources scientists
• Generative Modeling by Estimating Gradients of the Data Distribution
• Mixed Precision Training
• A Generative Model for Inverse Design of Metamaterials
• Interpolation Consistency Training for Semi-Supervised Learning
• Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics -- A Comprehensive Review
• Energy-based Generative Adversarial Network
• Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone
• Generating Videos with Scene Dynamics
• Density estimation using Real NVP
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Pose Guided Person Image Generation
• Adversarially Learned Inference
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• HDR image reconstruction from a single exposure using deep CNNs
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• The relativistic discriminator: a key element missing from standard GAN
• Object Detection in 20 Years: A Survey
• Data Synthesis based on Generative Adversarial Networks
• Semi-Supervised Learning with Generative Adversarial Networks
• FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Adversarial Attacks and Defences: A Survey
• Deep Generative Design: Integration of Topology Optimization and Generative Models
• Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images
• Unsupervised Cross-Domain Image Generation
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• Deep Anomaly Detection Using Geometric Transformations
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• Understanding the Role of Individual Units in a Deep Neural Network
• How Generative Adversarial Networks and Their Variants Work: An Overview
• NVAE: A Deep Hierarchical Variational Autoencoder
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Deep learning for determining a near-optimal topological design without any iteration
• Towards Principled Methods for Training Generative Adversarial Networks
• InfoVAE: Information Maximizing Variational Autoencoders
• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
• Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
• Systematic evaluation of CNN advances on the ImageNet
• WebVision Database: Visual Learning and Understanding from Web Data
• Differentially Private Generative Adversarial Network
• Deep Appearance Models for Face Rendering
• MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
• Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches
• Compressed Sensing using Generative Models
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Generative Adversarial Network for Medical Images (MI-GAN)
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
• Disentangling factors of variation in deep representations using adversarial training
• Image De-raining Using a Conditional Generative Adversarial Network
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Neural Photo Editing with Introspective Adversarial Networks
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• An Overview of Deep Semi-Supervised Learning
• MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
• Slimmable Neural Networks
• TI-CNN: Convolutional Neural Networks for Fake News Detection
• Generating Adversarial Examples with Adversarial Networks
• Syntax-Directed Variational Autoencoder for Structured Data
• Mode Regularized Generative Adversarial Networks
• On Convergence and Stability of GANs
• On the Reconstruction of Face Images from Deep Face Templates
• Triple Generative Adversarial Nets
• An empirical study on evaluation metrics of generative adversarial networks
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
• Generative Image Inpainting with Contextual Attention
• Synthesizing Tabular Data using Generative Adversarial Networks
• Rethinking the Value of Labels for Improving Class-Imbalanced Learning
• Adversarial Learning for Neural Dialogue Generation
• Stabilizing Training of Generative Adversarial Networks through Regularization
• Natural Language Processing Advancements By Deep Learning: A Survey
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Optimizing the Latent Space of Generative Networks
• Clustering with Deep Learning: Taxonomy and New Methods
• FiLM: Visual Reasoning with a General Conditioning Layer
• A Novel GAN-based Fault Diagnosis Approach for Imbalanced Industrial Time Series
• Anomaly Detection using One-Class Neural Networks
• Learning to Optimize Tensor Programs
• A Survey on Neural Speech Synthesis
• Learning a Driving Simulator
• In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
• TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning
• Learning in Implicit Generative Models
• From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques
• Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative Adversarial Nets
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Unmasking DeepFakes with simple Features
• L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
• The Numerics of GANs
• On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
• Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification
• Compressed Sensing with Deep Image Prior and Learned Regularization
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
• Simulator-based training of generative models for the inverse design of metasurfaces
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Adversarial Ranking for Language Generation
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Least Squares Generative Adversarial Networks
• Fighting Deepfake by Exposing the Convolutional Traces on Images
• An Overview of Machine Learning Techniques for Radiowave Propagation Modeling
• Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Multimodal Generative Models for Scalable Weakly-Supervised Learning
• Toward Controlled Generation of Text
• Learning Implicit Brain MRI Manifolds with Deep Learning
• VideoGPT: Video Generation using VQ-VAE and Transformers
• Deep Learning for Procedural Content Generation
• Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize
• Deep Identity-aware Transfer of Facial Attributes
• MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Isolating Sources of Disentanglement in Variational Autoencoders
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Advances in Deep Concealed Scene Understanding
• TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
• Vision-based Real Estate Price Estimation
• Optimization for deep learning: theory and algorithms
• On the regularization of Wasserstein GANs
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• Towards Deeper Understanding of Variational Autoencoding Models
• Do GANs actually learn the distribution? An empirical study
• SinGAN-Seg: Synthetic training data generation for medical image segmentation
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
• Video-to-Video Synthesis
• Dual Discriminator Generative Adversarial Nets
• AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
• Structure-Preserving Image Super-Resolution
• Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders
• Fighting deepfakes by detecting GAN DCT anomalies
• Grammar Variational Autoencoder
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• Multi-style Generative Network for Real-time Transfer
• Real-Time Adaptive Image Compression
• Synthetic Medical Images from Dual Generative Adversarial Networks
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Lifelong Generative Modeling
• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
• The Many-Body Expansion Combined with Neural Networks
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
• MaterialGAN: Reflectance Capture using a Generative SVBRDF Model
• Look Wider to Match Image Patches with Convolutional Neural Networks
• Is the deconvolution layer the same as a convolutional layer?
• Texture Synthesis with Spatial Generative Adversarial Networks
• HoloStain: Holographic virtual staining of individual biological cells
• Boundary-Seeking Generative Adversarial Networks
• Dataset Condensation with Gradient Matching
• One-Shot Unsupervised Cross Domain Translation
• Data-Free Adversarial Distillation
• Neural Style Transfer: A Review
• The Unusual Effectiveness of Averaging in GAN Training
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
• SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitro
• Adversarial Generation of Natural Language
• Roundtrip: A Deep Generative Neural Density Estimator
• What Do We Understand About Convolutional Networks?
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning
• Continual Learning in Generative Adversarial Nets
• Generative Models for Automatic Chemical Design
• Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
• Discovering state-parameter mappings in subsurface models using generative adversarial networks
• Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
• Incremental Classifier Learning with Generative Adversarial Networks
• Precise Recovery of Latent Vectors from Generative Adversarial Networks
• Soft-Label Dataset Distillation and Text Dataset Distillation
• Attribute2Image: Conditional Image Generation from Visual Attributes
• Vector-quantized Image Modeling with Improved VQGAN
• SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• Language Generation with Recurrent Generative Adversarial Networks without Pre-training
• Perceptual Generative Adversarial Networks for Small Object Detection
• GP-GAN: Towards Realistic High-Resolution Image Blending
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Motion Corrected Multishot MRI Reconstruction Using Generative Networks with Sensitivity Encoding
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Learning with privileged information via adversarial discriminative modality distillation
• Image-to-image translation for cross-domain disentanglement
• Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model
• FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction
• Universal Planning Networks
• Ansor: Generating High-Performance Tensor Programs for Deep Learning
• Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration
• Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
• Photographic Image Synthesis with Cascaded Refinement Networks
• Controlling generative models with continuous factors of variations
• Language GANs Falling Short
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Deep Directed Generative Models with Energy-Based Probability Estimation
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Cross-Resolution Learning for Face Recognition
• Local Aggregation for Unsupervised Learning of Visual Embeddings
• Data Augmentation in Emotion Classification Using Generative Adversarial Networks
• Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks
• Neural Stain-Style Transfer Learning using GAN for Histopathological Images
• Attacking Recommender Systems with Augmented User Profiles
• Dive into Deep Learning
• Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design
• BubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Images
• Adversarial Perturbations Against Real-Time Video Classification Systems
• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
• CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
• A-NICE-MC: Adversarial Training for MCMC
• Subsurface structure analysis using computational interpretation and learning: A visual signal processing perspective
• A Tutorial on Deep Learning for Music Information Retrieval
• A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• Few-Shot Learning with Geometric Constraints
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Stabilizing GAN Training with Multiple Random Projections
• Semantic Facial Expression Editing using Autoencoded Flow
• Super-resolution emulator of cosmological simulations using deep physical models
• Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks
• Spatial Image Steganography Based on Generative Adversarial Network
• On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
• Generalizing semi-supervised generative adversarial networks to regression using feature contrasting
• Collaborative Learning for Faster StyleGAN Embedding
• Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
• Low-Shot Learning from Imaginary Data
• Invariant Representations for Noisy Speech Recognition
• Deconvolutional Paragraph Representation Learning
• Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
• CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
• Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
• Improved Adversarial Systems for 3D Object Generation and Reconstruction
• Geometry Score: A Method For Comparing Generative Adversarial Networks
• Stabilizing Generative Adversarial Networks: A Survey
• Generative adversarial network with object detector discriminator for enhanced defect detection on ultrasonic B-scans
• Peeking Behind Objects: Layered Depth Prediction from a Single Image
• Conditional GAN for timeseries generation
• Adversarial Images for Variational Autoencoders
• Parametrization and generation of geological models with generative adversarial networks
• Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
• Compressing GANs using Knowledge Distillation
• PoNA: Pose-guided Non-local Attention for Human Pose Transfer
• Wasserstein Learning of Deep Generative Point Process Models
• Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
• Free-form tumor synthesis in computed tomography images via richer generative adversarial network
• PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• FIGR: Few-shot Image Generation with Reptile
• Damage detection using in-domain and cross-domain transfer learning
• RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
• Implicit Maximum Likelihood Estimation
• Improved StyleGAN Embedding: Where are the Good Latents?
• Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
• Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks
• Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
• i-RevNet: Deep Invertible Networks
• DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• Task Agnostic Continual Learning via Meta Learning
• Multiple-Human Parsing in the Wild
• Spatial Evolutionary Generative Adversarial Networks
• Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• WaveFlow: A Compact Flow-based Model for Raw Audio
• OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
• Temporal Prediction and Evaluation of Brassica Growth in the Field using Conditional Generative Adversarial Networks
• One-Sided Unsupervised Domain Mapping
• Unsupervised Histopathology Image Synthesis
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
• LOGAN: Latent Optimisation for Generative Adversarial Networks
• Detecting GAN generated Fake Images using Co-occurrence Matrices
• Learning by Association - A versatile semi-supervised training method for neural networks
• Anomaly Detection for Skin Disease Images Using Variational Autoencoder
• MAGAN: Margin Adaptation for Generative Adversarial Networks
• Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
• PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• Dataset Condensation with Differentiable Siamese Augmentation
• Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• Inverting face embeddings with convolutional neural networks
• Digital rock reconstruction with user-defined properties using conditional generative adversarial networks
• Multi-Generator Generative Adversarial Nets
• Going Deeper Into Face Detection: A Survey
• It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality
• Improved generator objectives for GANs
• RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Generative Modeling of Turbulence
• AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
• ControlVAE: Controllable Variational Autoencoder
• Coverless Information Hiding Based on Generative adversarial networks
• SSGAN: Secure Steganography Based on Generative Adversarial Networks
• Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis
• Generative Adversarial Nets from a Density Ratio Estimation Perspective
• GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Generative Image Translation for Data Augmentation in Colorectal Histopathology Images
• Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
• Toward Real-World Super-Resolution via Adaptive Downsampling Models
• Be Your Own Prada: Fashion Synthesis with Structural Coherence
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN
• CorrGAN: Sampling Realistic Financial Correlation Matrices Using Generative Adversarial Networks
• Is Generator Conditioning Causally Related to GAN Performance?
• DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
• MeshGAN: Non-linear 3D Morphable Models of Faces
• IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
• medigan: a Python library of pretrained generative models for medical image synthesis
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• Activation Maximization Generative Adversarial Nets
• Prescribed Generative Adversarial Networks
• A Hybrid Convolutional Variational Autoencoder for Text Generation
• Shift-Net: Image Inpainting via Deep Feature Rearrangement
• Generative adversarial networks in time series: A survey and taxonomy
• Deep Learning based HEp-2 Image Classification: A Comprehensive Review
• Unsupervised Text Style Transfer using Language Models as Discriminators
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
• Deep Learning-Guided Image Reconstruction from Incomplete Data
• Turing learning: a metric-free approach to inferring behavior and its application to swarms
• Stacked Generative Adversarial Networks
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
• Generative Language Modeling for Automated Theorem Proving
• Brain MRI super-resolution using 3D generative adversarial networks
• Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures
• A Survey of Optimization Methods from a Machine Learning Perspective
• Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
• A Spectral Approach to Gradient Estimation for Implicit Distributions
• Deep Robust Clustering by Contrastive Learning
• MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
• Deep Discriminative Clustering Analysis
• Progressive Pose Attention Transfer for Person Image Generation
• Object Discovery with a Copy-Pasting GAN
• FairGAN: Fairness-aware Generative Adversarial Networks
• A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA
• Human Motion Modeling using DVGANs
• StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
• Correction by Projection: Denoising Images with Generative Adversarial Networks
• Towards Large-Pose Face Frontalization in the Wild
• CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks
• Improving GANs Using Optimal Transport
• Comparison of Maximum Likelihood and GAN-based training of Real NVPs
• Container: Context Aggregation Network
• Semi-supervised Conditional GANs
• Unsupervised and semi-supervised learning with Categorical Generative Adversarial Networks assisted by Wasserstein distance for dermoscopy image Classification
• Deepfake Detection Scheme Based on Vision Transformer and Distillation
• Ensembles of Generative Adversarial Networks
• Void Filling of Digital Elevation Models with Deep Generative Models
• Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Convergence of Learning Dynamics in Stackelberg Games
• PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
• Generative Adversarial Self-Imitation Learning
• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
• ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
• End-to-End Speech-Driven Facial Animation with Temporal GANs
• Detecting and Simulating Artifacts in GAN Fake Images
• BourGAN: Generative Networks with Metric Embeddings
• A Convex Duality Framework for GANs
• Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
• Megapixel Size Image Creation using Generative Adversarial Networks
• Structure-Preserving Super Resolution with Gradient Guidance
• Class-Imbalanced Semi-Supervised Learning
• Watching the World Go By: Representation Learning from Unlabeled Videos
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• On the "steerability" of generative adversarial networks
• Recovering compressed images for automatic crack segmentation using generative models
• Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
• Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video
• Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
• ZhuSuan: A Library for Bayesian Deep Learning
• Privacy Adversarial Network: Representation Learning for Mobile Data Privacy
• Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
• SmartSeed: Smart Seed Generation for Efficient Fuzzing
• Anomaly Detection with Adversarial Dual Autoencoders
• Support-set bottlenecks for video-text representation learning
• Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis
• Deep Learning for Neuroimaging-based Diagnosis and Rehabilitation of Autism Spectrum Disorder: A Review
• Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming
• Contrastive Self-supervised Neural Architecture Search
• Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model
• Camera Style Adaptation for Person Re-identification
• GAN-based Hyperspectral Anomaly Detection
• Learning Hierarchical Features from Generative Models
• Novelty Detection with GAN
• Quaternion Generative Adversarial Networks
• Deep Back-Projection Networks for Single Image Super-resolution
• Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
• Deep Neural Networks for Pattern Recognition
• VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detection
• Temporal Generative Adversarial Nets with Singular Value Clipping
• Generating Images Part by Part with Composite Generative Adversarial Networks
• Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• Understanding Visual Concepts with Continuation Learning
• Contrastive Learning of Musical Representations
• Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
• Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
• Scene Text Synthesis for Efficient and Effective Deep Network Training
• Oriented Response Networks
• Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• Multi-view Generative Adversarial Networks
• Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss
• Towards Open-Set Identity Preserving Face Synthesis
• Conditional Adversarial Network for Semantic Segmentation of Brain Tumor
• Challenges in Disentangling Independent Factors of Variation
• Generative Counterfactual Introspection for Explainable Deep Learning
• Safer Classification by Synthesis
• Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
• Creativity: Generating Diverse Questions using Variational Autoencoders
• Visually-Aware Fashion Recommendation and Design with Generative Image Models
• Investigating Object Compositionality in Generative Adversarial Networks
• Small-GAN: Speeding Up GAN Training Using Core-sets
• F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
• Text to Image Synthesis Using Generative Adversarial Networks
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual Localization
• Class-Splitting Generative Adversarial Networks
• IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
• Pixel Deconvolutional Networks
• MGGAN: Solving Mode Collapse using Manifold Guided Training
• Evaluating vector-space models of analogy
• ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks
• Autoregressive Quantile Networks for Generative Modeling
• Semi-supervised deep learning by metric embedding
• Adversarial Learning with Local Coordinate Coding
• The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
• Differentially Private Data Generative Models
• Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
• Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
• Semi-Supervised Learning of Bearing Anomaly Detection via Deep Variational Autoencoders
• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
• Using latent space regression to analyze and leverage compositionality in GANs
• Generative Image Translation for Data Augmentation of Bone Lesion Pathology
• Generative Adversarial Parallelization
• Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN
• Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images
• Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging
• On the Benefit of Adversarial Training for Monocular Depth Estimation
• Synthesis of Realistic ECG using Generative Adversarial Networks
• Mask-aware Photorealistic Face Attribute Manipulation
• Simple yet Effective Way for Improving the Performance of GAN
• Focal Frequency Loss for Image Reconstruction and Synthesis
• Deep Synthetic Minority Over-Sampling Technique
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• AutoLoss: Learning Discrete Schedules for Alternate Optimization
• Generalized Capsule Networks with Trainable Routing Procedure
• Adversarial score matching and improved sampling for image generation
• Style2Vec: Representation Learning for Fashion Items from Style Sets
• Landmark Assisted CycleGAN for Cartoon Face Generation
• Laplacian Smoothing Gradient Descent
• AlphaGAN: Generative adversarial networks for natural image matting
• Pose-Normalized Image Generation for Person Re-identification
• A Systematic Survey of Deep Learning-based Single-Image Super-Resolution
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
• Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
• Amortized Variational Inference: A Systematic Review
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Counterfactuals uncover the modular structure of deep generative models
• Deep Learning for Free-Hand Sketch: A Survey
• BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Improved Training of Generative Adversarial Networks Using Representative Features
• Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models
• SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays
• 3D Object Reconstruction from a Single Depth View with Adversarial Learning
• Distinguishing mirror from glass: A 'big data' approach to material perception
• SurfNet: Generating 3D shape surfaces using deep residual networks
• Deep Learning on Image Denoising: An overview
• Global Texture Enhancement for Fake Face Detection in the Wild
• CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
• Improved Consistency Regularization for GANs
• Video Imagination from a Single Image with Transformation Generation
• ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks
• Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping
• Fully Automated Segmentation of Hyperreflective Foci in Optical Coherence Tomography Images
• Adversarial Generation of Continuous Implicit Shape Representations
• Deep Back-Projection Networks For Super-Resolution
• Scribbler: Controlling Deep Image Synthesis with Sketch and Color
• Generative Modeling with Conditional Autoencoders: Building an Integrated Cell
• Two Simple Ways to Learn Individual Fairness Metrics from Data
• Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
• High-resolution Deep Convolutional Generative Adversarial Networks
• GANs May Have No Nash Equilibria
• Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records
• Learning image representations for anomaly detection: application to discovery of histological alterations in drug development
• Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
• Recent Advances in Deep Learning for Object Detection
• McGan: Mean and Covariance Feature Matching GAN
• Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
• Structured Generative Adversarial Networks
• GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
• On Demand Solid Texture Synthesis Using Deep 3D Networks
• Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination
• TextureGAN: Controlling Deep Image Synthesis with Texture Patches
• VITON: An Image-based Virtual Try-on Network
• Hierarchical Autoregressive Image Models with Auxiliary Decoders
• Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
• Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering
• Photo-Realistic Video Prediction on Natural Videos of Largely Changing Frames
• Nonlinear 3D Face Morphable Model
• Time-Agnostic Prediction: Predicting Predictable Video Frames
• Business (mis)Use Cases of Generative AI
• Medical Image Synthesis with Context-Aware Generative Adversarial Networks
• Image Colorization Using a Deep Convolutional Neural Network
• DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
• DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
• Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies
• Defending Against Adversarial Attacks by Leveraging an Entire GAN
• Comparative Study on Generative Adversarial Networks
• Adversarial Time-to-Event Modeling
• Learning Texture Manifolds with the Periodic Spatial GAN
• Semi-supervised Image Attribute Editing using Generative Adversarial Networks
• A Probe Towards Understanding GAN and VAE Models
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• RED: A ReRAM-based Deconvolution Accelerator
• Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
• MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
• No More Discrimination: Cross City Adaptation of Road Scene Segmenters
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Text-to-Image-to-Text Translation using Cycle Consistent Adversarial Networks
• DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks
• Enriched Music Representations with Multiple Cross-modal Contrastive Learning
• Skill Rating for Generative Models
• Statistical Predictions in String Theory and Deep Generative Models
• StyleGAN2 Distillation for Feed-forward Image Manipulation
• Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
• Attribute-Guided Face Generation Using Conditional CycleGAN
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
• Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• Robust Compressive Phase Retrieval via Deep Generative Priors
• A survey of face recognition techniques under occlusion
• Robust Estimation and Generative Adversarial Nets
• Inverse reinforcement learning for video games
• Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
• Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
• Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
• Poisoning the Unlabeled Dataset of Semi-Supervised Learning
• Image inpainting using frequency domain priors
• GeoGAN: A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images
• Deep Generative Modeling for Scene Synthesis via Hybrid Representations
• Transferring GANs: generating images from limited data
• Locality and compositionality in zero-shot learning
• Towards causal generative scene models via competition of experts
• CoT: Cooperative Training for Generative Modeling of Discrete Data
• Bandwidth Extension on Raw Audio via Generative Adversarial Networks
• Global-Local Face Upsampling Network
• MRI Cross-Modality NeuroImage-to-NeuroImage Translation
• Towards resilient machine learning for ransomware detection
• Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
• Text-to-Face Generation with StyleGAN2
• QGAN: Quantized Generative Adversarial Networks
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Causal Generative Domain Adaptation Networks
• Disentangled Makeup Transfer with Generative Adversarial Network
• An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
• A novel topology design approach using an integrated deep learning network architecture
• GANsfer Learning: Combining labelled and unlabelled data for GAN based data augmentation
• RUN:Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection
• Attacking Speaker Recognition With Deep Generative Models
• Synthesizing Filamentary Structured Images with GANs
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• Smoothness and Stability in GANs
• Encoding Invariances in Deep Generative Models
• Fast and Provable ADMM for Learning with Generative Priors
• Generative adversarial networks and adversarial methods in biomedical image analysis
• Towards Robust Neural Machine Translation
• Scaling the Scattering Transform: Deep Hybrid Networks
• Generalised gravitational burst generation with Generative Adversarial Networks
• Adversarial Information Factorization
• Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
• ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks
• An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
• Exploring the Evolution of GANs through Quality Diversity
• Neumann Networks for Inverse Problems in Imaging
• Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
• Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss
• Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
• 3D Shape Induction from 2D Views of Multiple Objects
• SWAGAN: A Style-based Wavelet-driven Generative Model
• eCommerceGAN : A Generative Adversarial Network for E-commerce
• Conditional Image-to-Image Translation
• PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks
• On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach
• Deep Comprehensive Correlation Mining for Image Clustering
• Adversarial Network Bottleneck Features for Noise Robust Speaker Verification
• Estimating and Improving Fairness with Adversarial Learning
• Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
• Generative Latent Flow
• Physics-aware registration based auto-encoder for convection dominated PDEs
• Generative Adversarial Networks as Variational Training of Energy Based Models
• Mimicry: Towards the Reproducibility of GAN Research
• Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration
• Unsupervised Two-Stage Anomaly Detection
• Feature Re-Learning with Data Augmentation for Video Relevance Prediction
• Metropolis-Hastings Generative Adversarial Networks
• A Spectral Regularizer for Unsupervised Disentanglement
• Unsupervised Person Image Synthesis in Arbitrary Poses
• IQ of Neural Networks
• Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds
• Learning Autoencoders with Relational Regularization
• Some Theoretical Insights into Wasserstein GANs
• Knowledge Cross-Distillation for Membership Privacy
• Dynamics-aware Embeddings
• HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
• Diving Deeper into Underwater Image Enhancement: A Survey
• U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical Instrument
• Message Passing Multi-Agent GANs
• Overcoming Language Priors in Visual Question Answering with Adversarial Regularization
• Evaluating deep variational autoencoders trained on pan-cancer gene expression
• How Well Do WGANs Estimate the Wasserstein Metric?
• Robust Cross-View Gait Recognition with Evidence: A Discriminant Gait GAN (DiGGAN) Approach
• Human Motion Prediction via Spatio-Temporal Inpainting
• Deep UL2DL: Channel Knowledge Transfer from Uplink to Downlink
• Finding Mixed Nash Equilibria of Generative Adversarial Networks
• Counterfactual States for Atari Agents via Generative Deep Learning
• TorchGAN: A Flexible Framework for GAN Training and Evaluation
• Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs
• Comprehension-guided referring expressions
• On the Effectiveness of Least Squares Generative Adversarial Networks
• An error analysis of generative adversarial networks for learning distributions
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• The Riemannian Geometry of Deep Generative Models
• A Generative Adversarial Network for AI-Aided Chair Design
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• Justifying Diagnosis Decisions by Deep Neural Networks
• Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification
• Negative Momentum for Improved Game Dynamics
• Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder
• Programmable Neural Network Trojan for Pre-Trained Feature Extractor
• The iNaturalist Species Classification and Detection Dataset
• Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
• Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data
• This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces
• To Go or Not To Go? A Near Unsupervised Learning Approach For Robot Navigation
• Actively Learning what makes a Discrete Sequence Valid
• Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs
• A step towards procedural terrain generation with GANs
• Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
• Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
• Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
• A Mathematical Introduction to Generative Adversarial Nets (GAN)
• Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach Using MAESTRO
• Deep Generative Models for Distribution-Preserving Lossy Compression
• DOOM Level Generation using Generative Adversarial Networks
• Synthetic Data Generation for Fraud Detection using GANs
• Facial Aging and Rejuvenation by Conditional Multi-Adversarial Autoencoder with Ordinal Regression
• Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interactions
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• Ranking CGANs: Subjective Control over Semantic Image Attributes
• Real or Not Real, that is the Question
• Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
• 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
• Packet-Level Adversarial Network Traffic Crafting using Sequence Generative Adversarial Networks
• Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
• Stein Neural Sampler
• AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
• DeepCancer: Detecting Cancer through Gene Expressions via Deep Generative Learning
• Membership Model Inversion Attacks for Deep Networks
• Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks
• Deep unsupervised learning through spatial contrasting
• Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
• Triple consistency loss for pairing distributions in GAN-based face synthesis
• Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
• Puzzle-AE: Novelty Detection in Images through Solving Puzzles
• CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
• Exposing GAN-synthesized Faces Using Landmark Locations
• Deep Feature Consistent Variational Autoencoder
• WebVision Challenge: Visual Learning and Understanding With Web Data
• Prediction Under Uncertainty with Error-Encoding Networks
• Facelet-Bank for Fast Portrait Manipulation
• Procedural content generation of puzzle games using conditional generative adversarial networks
• CMB-GAN: Fast Simulations of Cosmic Microwave background anisotropy maps using Deep Learning
• Statistical guarantees for generative models without domination
• Disentangling Latent Hands for Image Synthesis and Pose Estimation
• Building robust classifiers through generation of confident out of distribution examples
• Generative Models as Distributions of Functions
• Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
• A Secure Mobile Authentication Alternative to Biometrics
• Effect of The Latent Structure on Clustering with GANs
• Better accuracy with quantified privacy: representations learned via reconstructive adversarial network
• Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN
• ACE: Adapting to Changing Environments for Semantic Segmentation
• Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
• AnonymousNet: Natural Face De-Identification with Measurable Privacy
• AdversarialNAS: Adversarial Neural Architecture Search for GANs
• Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets
• Creatism: A deep-learning photographer capable of creating professional work
• Light Convolutional Neural Network with Feature Genuinization for Detection of Synthetic Speech Attacks
• Active Image Synthesis for Efficient Labeling
• Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
• Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
• What Will Your Child Look Like? DNA-Net: Age and Gender Aware Kin Face Synthesizer
• Cross-domain Human Parsing via Adversarial Feature and Label Adaptation
• Improving Video Generation for Multi-functional Applications
• Adaptive Affinity Fields for Semantic Segmentation
• DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
• Deep learning for Gaussian process tomography model selection using the ASDEX Upgrade SXR system
• Linear Time Sinkhorn Divergences using Positive Features
• Quantitatively Evaluating GANs With Divergences Proposed for Training
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
• TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
• Teacher-Student Compression with Generative Adversarial Networks
• Deep cross-modality (MR-CT) educed distillation learning for cone beam CT lung tumor segmentation
• Spectral Regularization for Combating Mode Collapse in GANs
• Artificial Intelligence for Interstellar Travel
• Disentangling Factors of Variation by Mixing Them
• TequilaGAN: How to easily identify GAN samples
• A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy
• Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
• SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images
• Pulsar Candidate Identification with Artificial Intelligence Techniques
• Ways of Conditioning Generative Adversarial Networks
• Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
• Lipizzaner: A System That Scales Robust Generative Adversarial Network Training
• GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks
• Unsupervised Image Noise Modeling with Self-Consistent GAN
• Recent Progress of Face Image Synthesis
• Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
• LOGAN: Membership Inference Attacks Against Generative Models
• Image Morphing with Perceptual Constraints and STN Alignment
• CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation
• X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
• An Algorithm for Learning Shape and Appearance Models without Annotations
• A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints
• Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations
• Distributional Adversarial Networks
• Blood Vessel Geometry Synthesis using Generative Adversarial Networks
• One-Class Adversarial Nets for Fraud Detection
• DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• Statistics of Deep Generated Images
• Expansion of Cyber Attack Data From Unbalanced Datasets Using Generative Techniques
• RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
• Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
• Game of Learning Bloch Equation Simulations for MR Fingerprinting
• Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression
• Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain
• Deep Semantic Face Deblurring
• New Era of Deeplearning-Based Malware Intrusion Detection: The Malware Detection and Prediction Based On Deep Learning
• Private Post-GAN Boosting
• MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation
• Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
• GAN "Steerability" without optimization
• Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios
• IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
• Doubly Contrastive Deep Clustering
• Composite Functional Gradient Learning of Generative Adversarial Models
• AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems
• Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models
• Learning Residual Images for Face Attribute Manipulation
• Machine Learning and Polymer Self-Consistent Field Theory in Two Spatial Dimensions
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Semantically Consistent Image Completion with Fine-grained Details
• Training Deep Energy-Based Models with f-Divergence Minimization
• Globally Injective ReLU Networks
• Adversarial nets with perceptual losses for text-to-image synthesis
• Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
• Unsupervised learning for concept detection in medical images: a comparative analysis
• Aspect-augmented Adversarial Networks for Domain Adaptation
• Adversarially Regularized Graph Attention Networks for Inductive Learning on Partially Labeled Graphs
• Anomaly Detection with Domain Adaptation
• Bangla Handwritten Digit Recognition and Generation
• Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
• Generative Adversarial Nets for Robust Scatter Estimation: A Proper Scoring Rule Perspective
• Training Generative Adversarial Networks Via Turing Test
• Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network
• Face-to-Parameter Translation for Game Character Auto-Creation
• Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
• Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee
• Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
• Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning
• How Turing parasites expand the computational landscape of digital life
• Fingerprint Spoof Generalization
• MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
• Unsupervised Anomaly Detection for X-Ray Images
• Alleviating Mode Collapse in GAN via Diversity Penalty Module
• High Resolution Millimeter Wave Imaging For Self-Driving Cars
• MulGAN: Facial Attribute Editing by Exemplar
• Is Discriminator a Good Feature Extractor?
• Automatic structured variational inference
• Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
• Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders
• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
• Comparing Generative Adversarial Network Techniques for Image Creation and Modification
• On the generalization of GAN image forensics
• Engineered Self-Organization for Resilient Robot Self-Assembly with Minimal Surprise
• Improved Training with Curriculum GANs
• Deep Learning with the Random Neural Network and its Applications
• Learning the Base Distribution in Implicit Generative Models
• Generative Adversarial Network based on Resnet for Conditional Image Restoration
• Detection, Attribution and Localization of GAN Generated Images
• Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
• Learning to Disentangle GAN Fingerprint for Fake Image Attribution
• Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
• Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
• Pose Guided Human Video Generation
• GILT: Generating Images from Long Text
• Semi-supervised GAN for Classification of Multispectral Imagery Acquired by UAVs
• Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation
• Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
• On the Suboptimality of Negative Momentum for Minimax Optimization
• Attentive Adversarial Learning for Domain-Invariant Training
• High-Resolution Network for Photorealistic Style Transfer
• Unsupervised RGBD Video Object Segmentation Using GANs
• Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance
• A spin-glass model for the loss surfaces of generative adversarial networks
• Human Motion Transfer from Poses in the Wild
• Optimal transport maps for distribution preserving operations on latent spaces of Generative Models
• Understanding the (un)interpretability of natural image distributions using generative models
• Deep Clustering by Semantic Contrastive Learning
• Realistic Ultrasound Image Synthesis for Improved Classification of Liver Disease
• PolyGAN: High-Order Polynomial Generators
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
• Spatial Frequency Loss for Learning Convolutional Autoencoders
• Order and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts
• Robust utility maximization under model uncertainty via a penalization approach
• cGAN-based Manga Colorization Using a Single Training Image
• Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
• Towards Information-Seeking Agents
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
• Learning to Detect Fake Face Images in the Wild
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
• Annealed Generative Adversarial Networks
• Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
• Associative Adversarial Networks
• Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
• EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
• Hierarchical Detail Enhancing Mesh-Based Shape Generation with 3D Generative Adversarial Network
• Learning from Natural Noise to Denoise Micro-Doppler Spectrogram
• Metropolis-Hastings view on variational inference and adversarial training
• Generative Adversarial Networks with Decoder-Encoder Output Noise
• Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation
• The Neural Painter: Multi-Turn Image Generation
• Triple Generative Adversarial Networks
• (q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs
• A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
• How does Lipschitz Regularization Influence GAN Training?
• Model-Informed Generative Adversarial Network (MI-GAN) for Learning Optimal Power Flow
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• Variational Implicit Processes
• Learning Representations of Emotional Speech with Deep Convolutional Generative Adversarial Networks
• Autoencoder Image Interpolation by Shaping the Latent Space
• Information Maximizing Visual Question Generation
• Multi-View Data Generation Without View Supervision
• Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative
• Self-Supervised Feature Learning by Learning to Spot Artifacts
• An Improved Self-supervised GAN via Adversarial Training
• Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network
• SAD-GAN: Synthetic Autonomous Driving using Generative Adversarial Networks
• Face Translation between Images and Videos using Identity-aware CycleGAN
• ACtuAL: Actor-Critic Under Adversarial Learning
• Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
• Generate Identity-Preserving Faces by Generative Adversarial Networks
• Fence GAN: Towards Better Anomaly Detection
• Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
• Trustworthy AI in the Age of Pervasive Computing and Big Data
• Data Augmentation Using Adversarial Training for Construction-Equipment Classification
• Few-shot Video-to-Video Synthesis
• Facial Expression Recognition Using Disentangled Adversarial Learning
• Deep Image Clustering with Category-Style Representation
• Progressive Point Cloud Deconvolution Generation Network
• Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer
• Generating Realistic Stock Market Order Streams
• MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
• Generalization and Memorization: The Bias Potential Model
• A Data-Centric Approach for Training Deep Neural Networks with Less Data
• Diffusion Priors In Variational Autoencoders
• One-Shot Generative Domain Adaptation
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• Learning Neighborhood Representation from Multi-Modal Multi-Graph: Image, Text, Mobility Graph and Beyond
• Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
• Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
• CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
• Group Equivariant Generative Adversarial Networks
• ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image
• Propagation Channel Modeling by Deep learning Techniques
• QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with Increased Receptive Field
• Transformable Bottleneck Networks
• Face Completion with Semantic Knowledge and Collaborative Adversarial Learning
• Self-Supervised GAN to Counter Forgetting
• Deep Inception Generative Network for Cognitive Image Inpainting
• Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
• Low-Dose CT via Deep CNN with Skip Connection and Network in Network
• Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
• Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
• Self-Supervised Relative Depth Learning for Urban Scene Understanding
• Contextual-based Image Inpainting: Infer, Match, and Translate
• Aesthetic-Driven Image Enhancement by Adversarial Learning
• Learning Diverse Image Colorization
• Bottleneck Conditional Density Estimation
• Disentangled Representations in Neural Models
• Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
• Automatically Searching for U-Net Image Translator Architecture
• Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
• Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
• Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases
• AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation
• Palm-GAN: Generating Realistic Palmprint Images Using Total-Variation Regularized GAN
• Fully-Featured Attribute Transfer
• Reconstructing ERP Signals Using Generative Adversarial Networks for Mobile Brain-Machine Interface
• Learning about an exponential amount of conditional distributions
• Teaching GANs to Sketch in Vector Format
• LaSO: Label-Set Operations networks for multi-label few-shot learning
• Positional Encoding as Spatial Inductive Bias in GANs
• Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis
• Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks
• Self-Supervised GANs with Label Augmentation
• An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation
• Chinese Typeface Transformation with Hierarchical Adversarial Network
• GANosaic: Mosaic Creation with Generative Texture Manifolds
• Gaussian mixture models with Wasserstein distance
• Handloom Design Generation Using Generative Networks
• Structured Generative Models for Scene Understanding
• DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
• Novelty Detection via Non-Adversarial Generative Network
• Generative Minimization Networks: Training GANs Without Competition
• Super-resolution Variational Auto-Encoders
• Face Synthesis with Landmark Points from Generative Adversarial Networks and Inverse Latent Space Mapping
• Generating High Quality Visible Images from SAR Images Using CNNs
• RankGAN: A Maximum Margin Ranking GAN for Generating Faces
• Image Synthesis From Reconfigurable Layout and Style
• Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
• Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
• Compositional Visual Generation and Inference with Energy Based Models
• Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
• PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
• Understanding and Stabilizing GANs' Training Dynamics with Control Theory
• Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization
• LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network
• Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models
• MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN
• DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution
• Deep Learning Convective Flow Using Conditional Generative Adversarial Networks
• On Scalable and Efficient Computation of Large Scale Optimal Transport
• Deep Cross-Modal Audio-Visual Generation
• Conditional Density Estimation, Latent Variable Discovery and Optimal Transport
• Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
• A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
• Constrained Generative Adversarial Network Ensembles for Sharable Synthetic Data Generation
• Predicting Rapid Fire Growth (Flashover) Using Conditional Generative Adversarial Networks
• A Large-scale Attribute Dataset for Zero-shot Learning
• GAN-based Generation and Automatic Selection of Explanations for Neural Networks
• Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
• Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification
• Image-derived generative modeling of pseudo-macromolecular structures - towards the statistical assessment of Electron CryoTomography template matching
• SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
• Recursive Inference for Variational Autoencoders
• Multimodal Generative Models for Compositional Representation Learning
• Trumpets: Injective Flows for Inference and Inverse Problems
• On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
• CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Performing Co-Membership Attacks Against Deep Generative Models
• GAN-enhanced Conditional Echocardiogram Generation
• Chest X-ray Inpainting with Deep Generative Models
• Kernel Implicit Variational Inference
• Decentralized Attribution of Generative Models
• On Accelerating Distributed Convex Optimizations
• Multimodal Shape Completion via Conditional Generative Adversarial Networks
• Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations
• PixelNN: Example-based Image Synthesis
• Visual Forecasting by Imitating Dynamics in Natural Sequences
• MUFold-SS: Protein Secondary Structure Prediction Using Deep Inception-Inside-Inception Networks
• Metric Learning-based Generative Adversarial Network
• Generative adversarial networks for generation and classification of physical rehabilitation movement episodes
• Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification
• GANs beyond divergence minimization
• SegAttnGAN: Text to Image Generation with Segmentation Attention
• A Novel Fusion of Attention and Sequence to Sequence Autoencoders to Predict Sleepiness From Speech
• A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis
• Neural Topic Modeling with Bidirectional Adversarial Training
• Unsupervised Learning Facial Parameter Regressor for Action Unit Intensity Estimation via Differentiable Renderer
• Context-Aware Semantic Inpainting
• Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation
• Train simultaneously, generalize better: Stability of gradient-based minimax learners
• Generative Models as a Data Source for Multiview Representation Learning
• SketchyCOCO: Image Generation from Freehand Scene Sketches
• Learning Implicit Generative Models with the Method of Learned Moments
• Adversarially Approximated Autoencoder for Image Generation and Manipulation
• Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
• Digital Cardan Grille: A Modern Approach for Information Hiding
• Semantic Segmentation by Improved Generative Adversarial Networks
• Deep Stacked Networks with Residual Polishing for Image Inpainting
• MR-GAN: Manifold Regularized Generative Adversarial Networks
• Text-to-Image Generation with Attention Based Recurrent Neural Networks
• A Unified Framework for Generalizable Style Transfer: Style and Content Separation
• On Attribution of Deepfakes
• Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
• Latent Space Explorations of Singing Voice Synthesis using DDSP
• Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN
• Generative Adversarial Networks for Model Order Reduction in Seismic Full-Waveform Inversion
• Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
• Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation
• Generate High Resolution Images With Generative Variational Autoencoder
• Transfer feature generating networks with semantic classes structure for zero-shot learning
• One-to-Many Network for Visually Pleasing Compression Artifacts Reduction
• Data-Free Learning of Student Networks
• GANs-NQM: A Generative Adversarial Networks based No Reference Quality Assessment Metric for RGB-D Synthesized Views
• Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation
• FReeNet: Multi-Identity Face Reenactment
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• Training VAEs Under Structured Residuals
• Self-labeled Conditional GANs
• Decoupled Learning for Conditional Adversarial Networks
• ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
• Stopping GAN Violence: Generative Unadversarial Networks
• DR-Net: Transmission Steered Single Image Dehazing Network with Weakly Supervised Refinement
• Attention-GAN for Object Transfiguration in Wild Images
• Thermal to Visible Synthesis of Face Images using Multiple Regions
• Tensorizing GAN with High-Order Pooling for Alzheimer's Disease Assessment
• Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
• Disentangled VAE Representations for Multi-Aspect and Missing Data
• Hybrid VAE: Improving Deep Generative Models using Partial Observations
• Factorized Adversarial Networks for Unsupervised Domain Adaptation
• Server, server in the cloud. Who is the fairest in the crowd?
• Semantic-aware Image Deblurring
• The Reincarnation of Grille Cipher: A Generative Approach
• FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
• Personalization of Saliency Estimation
• FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition
• Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
• AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
• Probabilistic Generative Adversarial Networks
• A Survey on Audio Synthesis and Audio-Visual Multimodal Processing
• Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
• Conditional generation of multi-modal data using constrained embedding space mapping
• Can GAN Learn Topological Features of a Graph?
• xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems
• Adversarial Image Alignment and Interpolation
• AI-Powered Social Bots
• ComicGAN: Text-to-Comic Generative Adversarial Network
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
• Parametric Complexity Bounds for Approximating PDEs with Neural Networks
• Supervised Adversarial Networks for Image Saliency Detection
• Improving Sequential Latent Variable Models with Autoregressive Flows
• ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Design
• Enhancement of seismic imaging: An innovative deep learning approach
• End-to-End Conditional GAN-based Architectures for Image Colourisation
• Interpreting intermediate convolutional layers in unsupervised acoustic word classification
• Variance Regularizing Adversarial Learning
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• Handwritten Chinese Font Generation with Collaborative Stroke Refinement
• Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process
• Attentive Action and Context Factorization
• Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning
• Learning to Transfer: Unsupervised Meta Domain Translation
• A Plug-in Method for Representation Factorization in Connectionist Models
• Universality Theorems for Generative Models
• Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
• Millimeter Wave Channel Modeling via Generative Neural Networks
• toon2real: Translating Cartoon Images to Realistic Images
• Multi-class Generative Adversarial Nets for Semi-supervised Image Classification
• MaCow: Masked Convolutional Generative Flow
• Unsupervised Data Imputation via Variational Inference of Deep Subspaces
• BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN
• A Wasserstein GAN model with the total variational regularization
• A Unified Analysis of Variational Inequality Methods: Variance Reduction, Sampling, Quantization and Coordinate Descent
• AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations
• Generative Adversarial Networks Synthesize Realistic OCT Images of the Retina
• Attentive Normalization for Conditional Image Generation
• Sinogram interpolation for sparse-view micro-CT with deep learning neural network
• Generative Dual Adversarial Network for Generalized Zero-shot Learning
• Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image Synthesis
• On the Diversity of Realistic Image Synthesis
• A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University
• LUCSS: Language-based User-customized Colourization of Scene Sketches
• Inference in Multi-Layer Networks with Matrix-Valued Unknowns
• A two-step machine learning approach for crop disease detection: an application of GAN and UAV technology
• OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
• From Natural to Artificial Camouflage: Components and Systems
• retina-VAE: Variationally Decoding the Spectrum of Macular Disease
• Deep Generative Learning via Variational Gradient Flow
• PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening
• Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
• Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis
• Deep Network Interpolation for Continuous Imagery Effect Transition
• GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
• Surfing: Iterative optimization over incrementally trained deep networks
• FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network
• Deformable Deep Convolutional Generative Adversarial Network in Microwave Based Hand Gesture Recognition System
• Leveraging Random Label Memorization for Unsupervised Pre-Training
• Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork
• Deep Adversarial Belief Networks
• A Personalized Affective Memory Neural Model for Improving Emotion Recognition
• Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images
• Generative Adversarial Forests for Better Conditioned Adversarial Learning
• EnvGAN: Adversarial Synthesis of Environmental Sounds for Data Augmentation
• Deep learning for pedestrians: backpropagation in CNNs
• MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
• Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks
• SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
• Hallucinating very low-resolution and obscured face images
• Influence Estimation for Generative Adversarial Networks
• Flow Contrastive Estimation of Energy-Based Models
• Shallow Encoder Deep Decoder (SEDD) Networks for Image Encryption and Decryption
• Robust Unsupervised Small Area Change Detection from SAR Imagery Using Deep Learning
• Quad-networks: unsupervised learning to rank for interest point detection
• Learning Temporal Transformations From Time-Lapse Videos
• Multi-View Frame Reconstruction with Conditional GAN
• Unsupervised Transfer Learning with Self-Supervised Remedy
• MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
• Deep Generative Learning via Schrödinger Bridge
• MHVAE: a Human-Inspired Deep Hierarchical Generative Model for Multimodal Representation Learning
• Generative Ratio Matching Networks
• Deep Generalized Convolutional Sum-Product Networks
• PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks
• Generalized Energy Based Models
• Live Face De-Identification in Video
• Unsupervised Learning using Pretrained CNN and Associative Memory Bank
• Audio-Visual Self-Supervised Terrain Type Discovery for Mobile Platforms
• Hyperprior Induced Unsupervised Disentanglement of Latent Representations
• Generating Magnetic Resonance Spectroscopy Imaging Data of Brain Tumours from Linear, Non-Linear and Deep Learning Models
• Sinkhorn Natural Gradient for Generative Models
• Unsupervised Dual Adversarial Learning for Anomaly Detection in Colonoscopy Video Frames
• ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
• Autonomously and Simultaneously Refining Deep Neural Network Parameters by a Bi-Generative Adversarial Network Aided Genetic Algorithm
• Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
• ByteSGAN: A Semi-supervised Generative Adversarial Network for Encrypted Traffic Classification of SDN Edge Gateway in Green Communication Network
• Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks
• AutoGAN: Robust Classifier Against Adversarial Attacks
• The LORACs prior for VAEs: Letting the Trees Speak for the Data
• StrokeCoder: Path-Based Image Generation from Single Examples using Transformers
• Training Deep Neural Network in Limited Precision
• Skin disease diagnosis with deep learning: a review
• ImagineNet: Restyling Apps Using Neural Style Transfer
• Generative Adversarial Classifier for Handwriting Characters Super-Resolution
• MMGAN: Manifold Matching Generative Adversarial Network
• Style Transfer Applied to Face Liveness Detection with User-Centered Models
• Learning Implicit Generative Models by Teaching Explicit Ones
• Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN
• Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification
• Learning Graph Topological Features via GAN
• GO Gradient for Expectation-Based Objectives
• Adversarial-based neural networks for affect estimations in the wild
• A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
• DeMIAN: Deep Modality Invariant Adversarial Network
• Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks
• Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip Connections
• Customizing an Adversarial Example Generator with Class-Conditional GANs
• r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
• CNNs and GANs in MRI-based cross-modality medical image estimation
• DDIPNet and DDIPNet+: Discriminant Deep Image Prior Networks for Remote Sensing Image Classification
• Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks
• Unsupervised multi-modal Styled Content Generation
• Generative Reversible Data Hiding by Image to Image Translation via GANs
• Backpropagation for Implicit Spectral Densities
• Beauty Learning and Counterfactual Inference
• Contrast Phase Classification with a Generative Adversarial Network
• Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging
• Modeling EEG data distribution with a Wasserstein Generative Adversarial Network to predict RSVP Events
• Building a Regular Decision Boundary with Deep Networks
• Manifold Interpolation for Large-Scale Multi-Objective Optimization via Generative Adversarial Networks
• Learning Disentangled Representations of Satellite Image Time Series
• Very Long Natural Scenery Image Prediction by Outpainting
• Manifold Fitting under Unbounded Noise
• Improved BiGAN training with marginal likelihood equalization
• DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• Generative Collaborative Networks for Single Image Super-Resolution
• Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
• Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders
• Reconstruction and Membership Inference Attacks against Generative Models
• Semi-supervised Learning using Adversarial Training with Good and Bad Samples
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
• Learning Personalized Representation for Inverse Problems in Medical Imaging Using Deep Neural Network
• Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
• M-GWAP: An Online and Multimodal Game With A Purpose in WordPress for Mental States Annotation
• Generating Image Sequence from Description with LSTM Conditional GAN
• Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
• Deep Convolutional GANs for Car Image Generation
• Fully Automated Image De-fencing using Conditional Generative Adversarial Networks
• Conditional Video Generation Using Action-Appearance Captions
• ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans
• Domain Adaptation Meets Disentangled Representation Learning and Style Transfer
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• A First Look at Deep Learning Apps on Smartphones
• CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
• Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization
• Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
• Image-to-Image Translation with Multi-Path Consistency Regularization
• Latent Dirichlet Allocation in Generative Adversarial Networks
• Cloud2Curve: Generation and Vectorization of Parametric Sketches
• Generative adversarial network based on chaotic time series
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
• An iterative framework for self-supervised deep speaker representation learning
• On Computation and Generalization of GANs with Spectrum Control
• Text Generation Based on Generative Adversarial Nets with Latent Variable
• Generative Image Modeling using Style and Structure Adversarial Networks
• Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
• Multi-future Merchant Transaction Prediction
• Deep Learned Frame Prediction for Video Compression
• Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
• Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance
• Global and Local Consistent Wavelet-domain Age Synthesis
• Reciprocal Adversarial Learning via Characteristic Functions
• Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions
• GLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features
• Entropy-regularized Optimal Transport Generative Models
• Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition
• PriorGAN: Real Data Prior for Generative Adversarial Nets
• Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
• An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks
• Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification
• Retinal Vessel Segmentation Based on Conditional Deep Convolutional Generative Adversarial Networks
• Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization
• Online Exemplar Fine-Tuning for Image-to-Image Translation
• TailorGAN: Making User-Defined Fashion Designs
• Depth Structure Preserving Scene Image Generation
• Model-Free Renewable Scenario Generation Using Generative Adversarial Networks
• Longitudinal Face Aging in the Wild - Recent Deep Learning Approaches
• Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Learning State Representations in Complex Systems with Multimodal Data
• Mode matching in GANs through latent space learning and inversion
• Decomposed Adversarial Learned Inference
• Adversarial Open-World Person Re-Identification
• Face Aging with Contextual Generative Adversarial Nets
• Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
• Adaptive Procedural Task Generation for Hard-Exploration Problems
• Federated Generative Adversarial Learning
• Segmentation Guided Image-to-Image Translation with Adversarial Networks
• Toward Joint Image Generation and Compression using Generative Adversarial Networks
• Translate-to-Recognize Networks for RGB-D Scene Recognition
• Improving the Performance of Fine-Grain Image Classifiers via Generative Data Augmentation
• Subsampled Fourier Ptychography using Pretrained Invertible and Untrained Network Priors
• Deep Self-Supervised Representation Learning for Free-Hand Sketch
• Efficient Cloth Simulation using Miniature Cloth and Upscaling Deep Neural Networks
• Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging
• Dual Adversarial Learning with Attention Mechanism for Fine-grained Medical Image Synthesis
• GAN-Knowledge Distillation for one-stage Object Detection
• Adversarial Pixel-Level Generation of Semantic Images
• Model Comparison of Dark Energy models Using Deep Network
• Generative Adversarial Mapping Networks
• Predicting Real-Time Locational Marginal Prices: A GAN-Based Video Prediction Approach
• MIASSR: An Approach for Medical Image Arbitrary Scale Super-Resolution
• Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
• Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation
• Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
• Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
• Image2GIF: Generating Cinemagraphs using Recurrent Deep Q-Networks
• Adaptive Weighted Discriminator for Training Generative Adversarial Networks
• Semantic Interpolation in Implicit Models
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss
• Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
• GAN-MDF: A Method for Multi-fidelity Data Fusion in Digital Twins
• Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
• Intra-class variation reduction of speaker representation in disentanglement framework
• Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
• SDE approximations of GANs training and its long-run behavior
• One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis
• Effective and Privacy preserving Tabular Data Synthesizing
• Performance Analysis and Characterization of Training Deep Learning Models on Mobile Devices
• Adversarial Recommendation: Attack of the Learned Fake Users
• Towards Grounding Conceptual Spaces in Neural Representations
• Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification
• Adversarial Constraint Learning for Structured Prediction
• BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
• A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
• End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
• CADA: Multi-scale Collaborative Adversarial Domain Adaptation for Unsupervised Optic Disc and Cup Segmentation
• Manifold-preserved GANs
• Latent Space Optimal Transport for Generative Models
• On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization
• Net2Vec: Deep Learning for the Network
• Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables
• Alleviation of Gradient Exploding in GANs: Fake Can Be Real
• DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Introspective Generative Modeling: Decide Discriminatively
• Training Wasserstein GANs without gradient penalties
• Gradient penalty from a maximum margin perspective
• MisConv: Convolutional Neural Networks for Missing Data
• CRAM: Clued Recurrent Attention Model
• Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
• Joint Learning of Neural Networks via Iterative Reweighted Least Squares
• Deconstructing Generative Adversarial Networks
• Learning a Hierarchical Latent-Variable Model of 3D Shapes
• Semi-supervised Complex-valued GAN for Polarimetric SAR Image Classification
• Learning to Reconstruct Crack Profiles for Eddy Current Nondestructive Testing
• An Auxiliary Classifier Generative Adversarial Framework for Relation Extraction
• Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
• Scarce Data Driven Deep Learning of Drones via Generalized Data Distribution Space
• Binocular Rivalry Oriented Predictive Auto-Encoding Network for Blind Stereoscopic Image Quality Measurement
• Collaborative Training of GANs in Continuous and Discrete Spaces for Text Generation
• Composable Unpaired Image to Image Translation
• One-to-one Mapping for Unpaired Image-to-image Translation
• BreGMN: scaled-Bregman Generative Modeling Networks
• Integrating Categorical Semantics into Unsupervised Domain Translation
• Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
• Discriminative Clustering for Robust Unsupervised Domain Adaptation
• Learning Manifold Implicitly via Explicit Heat-Kernel Learning
• Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
• DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
• Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution
• Sliced Wasserstein Generative Models
• Generating Unobserved Alternatives
• Orthogonal Wasserstein GANs
• Convergence and Sample Complexity of SGD in GANs
• Attribute-Driven Spontaneous Motion in Unpaired Image Translation
• Slimmable Generative Adversarial Networks
• Ward2ICU: A Vital Signs Dataset of Inpatients from the General Ward
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• Parametrization of stochastic inputs using generative adversarial networks with application in geology
• Balance Scene Learning Mechanism for Offshore and Inshore Ship Detection in SAR Images
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition
• Weakly Supervised Audio Source Separation via Spectrum Energy Preserved Wasserstein Learning
• DISCO Nets: DISsimilarity COefficient Networks
• Semi-Implicit Generative Model
• Natural and Effective Obfuscation by Head Inpainting
• Image Generation from Sketch Constraint Using Contextual GAN
• Batch Normalization in the final layer of generative networks
• Towards a continuous modeling of natural language domains
• Smoother Network Tuning and Interpolation for Continuous-level Image Processing
• PoseGAN: A Pose-to-Image Translation Framework for Camera Localization
• Inferring Personalized Bayesian Embeddings for Learning from Heterogeneous Demonstration
• General Probabilistic Surface Optimization and Log Density Estimation
• On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• Facial Information Recovery from Heavily Damaged Images using Generative Adversarial Network- PART 1
• Ensembling with Deep Generative Views
• Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack
• Collaborative Sampling in Generative Adversarial Networks
• Illumination Invariant Foreground Object Segmentation using ForeGANs
• Lipschitz Constrained GANs via Boundedness and Continuity
• Mixture of Spectral Generative Adversarial Networks for Imbalanced Hyperspectral Image Classification
• Semi-Supervised Learning for In-Game Expert-Level Music-to-Dance Translation
• A Decoupled 3D Facial Shape Model by Adversarial Training
• Systematic Analysis and Removal of Circular Artifacts for StyleGAN
• Automated Testing for Deep Learning Systems with Differential Behavior Criteria
• Dilated Temporal Relational Adversarial Network for Generic Video Summarization
• Accelerating Training of Deep Neural Networks with a Standardization Loss
• Deep Consensus Learning
• Graph Sparsification with Generative Adversarial Network
• Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior
• Adversarial Learning of Semantic Relevance in Text to Image Synthesis
• Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery
• Unsupervised learning with sparse space-and-time autoencoders
• Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition
• Entropy, Computing and Rationality
• Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks
• Generative Steganography by Sampling
• Few-shot Continual Learning: a Brain-inspired Approach
• Deep Context-Aware Novelty Detection
• SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation
• Ensembles of GANs for synthetic training data generation
• Evolvement Constrained Adversarial Learning for Video Style Transfer
• A Neuro-AI Interface for Evaluating Generative Adversarial Networks
• Semantic Image Manipulation Using Scene Graphs
• Max-Margin Deep Generative Models for (Semi-)Supervised Learning
• MUFold-BetaTurn: A Deep Dense Inception Network for Protein Beta-Turn Prediction
• Target Consistency for Domain Adaptation: when Robustness meets Transferability
• Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing
• Typeface Completion with Generative Adversarial Networks
• Go with the Flow: Adaptive Control for Neural ODEs
• When do GANs replicate? On the choice of dataset size
• Learn distributed GAN with Temporary Discriminators
• Deep learning approaches for neural decoding: from CNNs to LSTMs and spikes to fMRI
• MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
• Latent Neural Differential Equations for Video Generation
• On Positive-Unlabeled Classification in GAN
• RNN-based Generative Model for Fine-Grained Sketching
• Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images
• Using Generative Models for Pediatric wbMRI
• Reborn Mechanism: Rethinking the Negative Phase Information Flow in Convolutional Neural Network
• Learning Generative Models of Tissue Organization with Supervised GANs
• Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data
• Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Neural Networks
• Capsule GAN Using Capsule Network for Generator Architecture
• Reducing over-smoothness in speech synthesis using Generative Adversarial Networks
• Adversarial Likelihood-Free Inference on Black-Box Generator
• Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
• A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction
• Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples
• Paired 3D Model Generation with Conditional Generative Adversarial Networks
• Language Model Evaluation in Open-ended Text Generation
• Regularized Evolutionary Population-Based Training
• A Novel Framework for Selection of GANs for an Application
• Stable Distribution Alignment Using the Dual of the Adversarial Distance
• Artificial Neural Network for Cybersecurity: A Comprehensive Review
• Exemplar-based synthesis of geology using kernel discrepancies and generative neural networks
• Adversarial Robustness Guarantees for Random Deep Neural Networks
• FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing
• OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning
• Deep Markov Random Field for Image Modeling
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning
• Deep Sound Change: Deep and Iterative Learning, Convolutional Neural Networks, and Language Change
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
• A manifold learning perspective on representation learning: Learning decoder and representations without an encoder
• An Introduction to Variational Inference
• Latent Vector Recovery of Audio GANs
• Deep generative demixing: Recovering Lipschitz signals from noisy subgaussian mixtures
• Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications
• A Framework for Generative and Contrastive Learning of Audio Representations
• Boosting Supervised Learning Performance with Co-training
• Image Style Transfer and Content-Style Disentanglement
• Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
• From Rain Generation to Rain Removal
• Learning to Profile: User Meta-Profile Network for Few-Shot Learning
• EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
• Unsupervised Remote Sensing Super-Resolution via Migration Image Prior
• F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
• Towards a Neural Graphics Pipeline for Controllable Image Generation
• Computer-Assisted Analysis of Biomedical Images
• Noise Conditional Flow Model for Learning the Super-Resolution Space
• Neural Communication Systems with Bandwidth-limited Channel
• Unsupervised Vehicle Counting via Multiple Camera Domain Adaptation
• Free-viewpoint Indoor Neural Relighting from Multi-view Stereo
• Generative Modeling for Multi-task Visual Learning
• Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
• Interflow: Aggregating Multi-layer Feature Mappings with Attention Mechanism
• A New Distributed Method for Training Generative Adversarial Networks
• Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration
• Generative Models for Security: Attacks, Defenses, and Opportunities
• Making Method of Moments Great Again? -- How can GANs learn distributions
• Regularized Sequential Latent Variable Models with Adversarial Neural Networks
• G3AN: Disentangling Appearance and Motion for Video Generation
• Adaptive Divergence for Rapid Adversarial Optimization
• Detecting Invasive Ductal Carcinoma with Semi-Supervised Conditional GANs
• Can I teach a robot to replicate a line art
• GCCN: Global Context Convolutional Network
• Signature-Graph Networks
• Neural View-Interpolation for Sparse Light Field Video
• Electrocardio Panorama: Synthesizing New ECG Views with Self-supervision
• Data-free Knowledge Distillation for Segmentation using Data-Enriching GAN
• Transforming Facial Weight of Real Images by Editing Latent Space of StyleGAN
• Text Modeling with Syntax-Aware Variational Autoencoders
• Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma
• TunaGAN: Interpretable GAN for Smart Editing
• Adversarial View-Consistent Learning for Monocular Depth Estimation
• Enhance Gender and Identity Preservation in Face Aging Simulation for Infants and Toddlers
• Stylized Neural Painting
• HPC AI500: A Benchmark Suite for HPC AI Systems
• Mode Penalty Generative Adversarial Network with adapted Auto-encoder
• Digging Deeper into CRNN Model in Chinese Text Images Recognition
• Data-driven Accelerogram Synthesis using Deep Generative Models
• Complexity Controlled Generative Adversarial Networks
• Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks
• DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning
• A Cost Effective Solution for Road Crack Inspection using Cameras and Deep Neural Networks
• Flow-based Generative Models for Learning Manifold to Manifold Mappings
• The role of invariance in spectral complexity-based generalization bounds
• Structured 2D Representation of 3D Data for Shape Processing
• Automatic Face Understanding: Recognizing Families in Photos
• Road images augmentation with synthetic traffic signs using neural networks
• GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
• Cauchy-Schwarz Regularized Autoencoder
• A Spectral Enabled GAN for Time Series Data Generation
• Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
• SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms
• Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks
• Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
• Towards Unsupervised Single-Channel Blind Source Separation using Adversarial Pair Unmix-and-Remix
• Zero-shot Adversarial Quantization
• Spatial contrasting for deep unsupervised learning
• Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training
• Neural Video Portrait Relighting in Real-time via Consistency Modeling
• ChainGAN: A sequential approach to GANs
• Adversarial point set registration
• Guiding the One-to-one Mapping in CycleGAN via Optimal Transport
• Student's t-Generative Adversarial Networks
• Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization
• Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent
• Reproducing AmbientGAN: Generative models from lossy measurements
• LoGAN: Generating Logos with a Generative Adversarial Neural Network Conditioned on color
• Towards QoS-Aware and Resource-Efficient GPU Microservices Based on Spatial Multitasking GPUs In Datacenters
• In-Vehicle Object Detection in the Wild for Driverless Vehicles
• Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
• A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
• Steganography GAN: Cracking Steganography with Cycle Generative Adversarial Networks
• Sparse Label Smoothing Regularization for Person Re-Identification
• Online Kernel based Generative Adversarial Networks
• A Generative Neural Network Framework for Automated Software Testing
• Words as Art Materials: Generating Paintings with Sequential GANs
• Pose2RGBD. Generating Depth and RGB images from absolute positions
• DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
• Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation
• Interpreting Spatially Infinite Generative Models
• KinshipGAN: Synthesizing of Kinship Faces From Family Photos by Regularizing a Deep Face Network
• Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation
• Knowledge Efficient Deep Learning for Natural Language Processing
• Deep PDF: Probabilistic Surface Optimization and Density Estimation
• Neural Crossbreed: Neural Based Image Metamorphosis
• A Markov Decision Process Approach to Active Meta Learning
• Semantically Selective Augmentation for Deep Compact Person Re-Identification
• Inverse mapping of face GANs
• Attribute-conditioned Layout GAN for Automatic Graphic Design
• Hierarchy of GANs for learning embodied self-awareness model
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
• A Memristor based Unsupervised Neuromorphic System Towards Fast and Energy-Efficient GAN
• Steganography Security: Principle and Practice
• Evaluating a Generative Adversarial Framework for Information Retrieval
• Multi-level Feature Learning on Embedding Layer of Convolutional Autoencoders and Deep Inverse Feature Learning for Image Clustering
• On the Anomalous Generalization of GANs
• AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups
• Deep Unsupervised Clustering with Clustered Generator Model
• Simulating dysarthric speech for training data augmentation in clinical speech applications
• Predicting resonant properties of plasmonic structures by deep learning
• Facial Expression Representation Learning by Synthesizing Expression Images
• Detecting GAN generated errors
• High-Freedom Inverse Design with Deep Neural Network for Metasurface Filter in the Visible
• Adversarial Binary Coding for Efficient Person Re-identification
• Flipped-Adversarial AutoEncoders
• DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
• Generative Spatiotemporal Modeling Of Neutrophil Behavior
• Towards Deeper Generative Architectures for GANs using Dense connections
• A Study into the similarity in generator and discriminator in GAN architecture
• Purifying Real Images with an Attention-guided Style Transfer Network for Gaze Estimation
• GANILLA: Generative Adversarial Networks for Image to Illustration Translation
• Motion deblurring of faces
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE)
• Performance Evaluation of Deep Generative Models for Generating Hand-Written Character Images
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
• Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration
• Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
• Evolution of Images with Diversity and Constraints Using a Generator Network
• Spectral Image Visualization Using Generative Adversarial Networks
• Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets
• PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
• Disentangling Video with Independent Prediction
• Online Detection of Action Start in Untrimmed, Streaming Videos
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Single-View Food Portion Estimation: Learning Image-to-Energy Mappings Using Generative Adversarial Networks
• A Generative Map for Image-based Camera Localization
• Perturbative GAN: GAN with Perturbation Layers
• Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
• Towards Real-Time Advancement of Underwater Visual Quality with GAN
• Autonomy, Authenticity, Authorship and Intention in computer generated art
• Voice command generation using Progressive Wavegans
• Inserting Videos into Videos
• Learning Quadrangulated Patches For 3D Shape Processing
• Deep, spatially coherent Occupancy Maps based on Radar Measurements
• Restricting Greed in Training of Generative Adversarial Network
• Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling
• Kernel Mean Matching for Content Addressability of GANs
• Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation
• Reconstructing faces from voices
• Encoder-Powered Generative Adversarial Networks
• Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks
• Inferring 3D Shapes from Image Collections using Adversarial Networks
• Multi Resolution LSTM For Long Term Prediction In Neural Activity Video
• A Halo Merger Tree Generation and Evaluation Framework
• MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
• Learning to Avoid Errors in GANs by Manipulating Input Spaces
• Capturing the diversity of biological tuning curves using generative adversarial networks
• Implicit Manifold Learning on Generative Adversarial Networks
• One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
• Doppler-Radar Based Hand Gesture Recognition System Using Convolutional Neural Networks
• IVE-GAN: Invariant Encoding Generative Adversarial Networks
• Semi-Supervised Learning with IPM-based GANs: an Empirical Study
• Unsupervised Despeckling
• OpenICS: Open Image Compressive Sensing Toolbox and Benchmark
• Exploiting the Hidden Tasks of GANs: Making Implicit Subproblems Explicit
• A Stochastic Variance Reduced Primal Dual Fixed Point Method For Linearly Constrained Separable Optimization
• ViT-Inception-GAN for Image Colourising
• Improving Shape Deformation in Unsupervised Image-to-Image Translation
• 3D Topology Transformation with Generative Adversarial Networks
• BSD-GAN: Branched Generative Adversarial Network for Scale-Disentangled Representation Learning and Image Synthesis
• Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior
• Dist-GAN: An Improved GAN using Distance Constraints
• Directional GAN: A Novel Conditioning Strategy for Generative Networks
• Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions
• Inner Space Preserving Generative Pose Machine
• Face-to-Music Translation Using a Distance-Preserving Generative Adversarial Network with an Auxiliary Discriminator
• Regularizing Deep Hashing Networks Using GAN Generated Fake Images
• Escaping from Collapsing Modes in a Constrained Space
• Intrusive deconvolutional neural networks for enhancing PIC/FLIP solutions
• Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks
• How many labeled license plates are needed?
• AM-DCGAN: Analog Memristive Hardware Accelerator for Deep Convolutional Generative Adversarial Networks
• From DNNs to GANs: Review of efficient hardware architectures for deep learning
• Deep Convolutional Generative Adversarial Network Based Food Recognition Using Partially Labeled Data
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
• A Robust Attentional Framework for License Plate Recognition in the Wild
• Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery
• Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
• Learning to infer in recurrent biological networks
• Barcode Method for Generative Model Evaluation driven by Topological Data Analysis
• Interpretable BoW Networks for Adversarial Example Detection
• Image Manipulation with Perceptual Discriminators
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• Latent Space Exploration Using Generative Kernel PCA
• A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM
• Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks
• Understanding Fake Faces
• Selective Sampling and Mixture Models in Generative Adversarial Networks
• Hyperbolic Manifold Regression
• Coulomb Autoencoders
• BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images
• Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model
• Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
• Local Stability and Performance of Simple Gradient Penalty mu-Wasserstein GAN
• Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation
• Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face
• Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network
• Composition and decomposition of GANs
• Cross-Resolution Person Re-identification with Deep Antithetical Learning
• Concept Formation and Dynamics of Repeated Inference in Deep Generative Models
• Compressed Sensing via Measurement-Conditional Generative Models
• Virtual Conditional Generative Adversarial Networks
• Diversity Regularized Adversarial Learning
• GAN pretraining for deep convolutional autoencoders applied to Software-based Fingerprint Presentation Attack Detection
• Minority Class Oversampling for Tabular Data with Deep Generative Models
• Stay Positive: Non-Negative Image Synthesis for Augmented Reality
• Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition
• Stochastic primal dual fixed point method for composite optimization
• On the Limits of Learning Representations with Label-Based Supervision
• Multi-modal Datasets for Super-resolution
• Generating the support with extreme value losses
• Convergence of GANs Training: A Game and Stochastic Control Methodology
• Synthesizing New Retinal Symptom Images by Multiple Generative Models
• Incremental Scene Synthesis
• Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
• Representation Learning by Reconstructing Neighborhoods
• An Interpretable Generative Model for Handwritten Digit Image Synthesis
• Surrogate Gradient Field for Latent Space Manipulation
• Label-Removed Generative Adversarial Networks Incorporating with K-Means
• Fast Face Image Synthesis with Minimal Training
• Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders
• Deep Chaos Synchronization
• Adversarial Machine Learning-Enabled Anonymization of OpenWiFi Data
• Linear Semantics in Generative Adversarial Networks
• Context Encoding Chest X-rays
• Joint Distribution across Representation Space for Out-of-Distribution Detection
• A Bayesian Approach to Identifying Representational Errors
• Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
• Mean Field Game GAN
• Let's Transfer Transformations of Shared Semantic Representations
• Traversing Latent Space using Decision Ferns
• Towards a Uniform Architecture for the Efficient Implementation of 2D and 3D Deconvolutional Neural Networks on FPGAs
• Generative Steganography with Kerckhoffs' Principle
• OmiTrans: generative adversarial networks based omics-to-omics translation framework
• Vanishing Twin GAN: How training a weak Generative Adversarial Network can improve semi-supervised image classification
• Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery
• Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence
• Towards Disentangling Latent Space for Unsupervised Semantic Face Editing
• Parallel Medical Imaging for Intelligent Medical Image Analysis: Concepts, Methods, and Applications
• Purifying Naturalistic Images through a Real-time Style Transfer Semantics Network
• Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
• Identifying Human Edited Images using a CNN
• The reinforcement learning-based multi-agent cooperative approach for the adaptive speed regulation on a metallurgical pickling line
• CNN with large memory layers
• Predicting future astronomical events using deep learning
• Toroidal AutoEncoder
• Normalized Diversification
• Invexifying Regularization of Non-Linear Least-Squares Problems
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
• GAN You Do the GAN GAN?
• Analysis of Macula on Color Fundus Images Using Heightmap Reconstruction Through Deep Learning
• SimuGAN: Unsupervised forward modeling and optimal design of a LIDAR Camera
• Vision-based Price Suggestion for Online Second-hand Items
• FakeSafe: Human Level Data Protection by Disinformation Mapping using Cycle-consistent Adversarial Network
• Is 'Unsupervised Learning' a Misconceived Term?
• Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
• Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation
• Learning Equivariant Representations
• Reconstructing Network Inputs with Additive Perturbation Signatures
• MakeupBag: Disentangling Makeup Extraction and Application
• Shakeout: A New Approach to Regularized Deep Neural Network Training
• Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case
• Deep Learning based Urban Vehicle Trajectory Analytics
• A Two-Step Disentanglement Method
• Accelerating Distributed SGD for Linear Regression using Iterative Pre-Conditioning
• Processsing Simple Geometric Attributes with Autoencoders
• Analyzing the benefits of communication channels between deep learning models
• TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
• A study of traits that affect learnability in GANs
• Introducing a Generative Adversarial Network Model for Lagrangian Trajectory Simulation
• Video SemNet: Memory-Augmented Video Semantic Network
• GAN based ball screw drive picture database enlargement for failure classification
• Boosting Generative Models by Leveraging Cascaded Meta-Models
• SetGAN: Improving the stability and diversity of generative models through a permutation invariant architecture
• Generating Diverse Realistic Laughter for Interactive Art
• Modelling and simulating spatial extremes by combining extreme value theory with generative adversarial networks
• Boosting Scene Character Recognition by Learning Canonical Forms of Glyphs
• Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks
• Creation of Synthetic Networked PMU Data: A Generative Adversarial Network Approach
• Adversarial Training for Code Retrieval with Question-Description Relevance Regularization
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image
• Real-time Locational Marginal Price Forecasting Using Generative Adversarial Network
• Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
• PicHunt: Social Media Image Retrieval for Improved Law Enforcement
• Localising In Complex Scenes Using Balanced Adversarial Adaptation
• Efficient Semantic Image Synthesis via Class-Adaptive Normalization
• Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution
• Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images
• Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network
• Assessing Automated Machine Learning service to detect COVID-19 from X-Ray and CT images: A Real-time Smartphone Application case study
• Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding
• Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection
• The Implicit Metropolis-Hastings Algorithm
• Learning Priors for Adversarial Autoencoders
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• WeightAlign: Normalizing Activations by Weight Alignment
• $\rho$-VAE: Autoregressive parametrization of the VAE encoder
• MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization
• Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolution
• Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
• Using colorization as a tool for automatic makeup suggestion
• Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
• Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks
• Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision
• Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
• Toward Privacy and Utility Preserving Image Representation
• A Semi-Supervised Approach for Automatic Crystal Structure Classification
• PIE: Pseudo-Invertible Encoder
• Not Just Cloud Privacy: Protecting Client Privacy in Teacher-Student Learning
• ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network
• Multilayer Lookahead: a Nested Version of Lookahead
• Artistic Autonomy in AI Art
• Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation
• Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis
• Deep Human-guided Conditional Variational Generative Modeling for Automated Urban Planning
• Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning
• 3N-GAN: Semi-Supervised Classification of X-Ray Images with a 3-Player Adversarial Framework
• Generative Adversarial Networks for Multimodal Representation Learning in Video Hyperlinking
• Challenges and Solutions in DeepFakes
• Self-Supervised Neural Architecture Search for Imbalanced Datasets
• StackGAN: Facial Image Generation Optimizations
• Multi-Attributed and Structured Text-to-Face Synthesis
• Reducing the Representation Error of GAN Image Priors Using the Deep Decoder
• Zoom, Enhance! Measuring Surveillance GAN Up-sampling
• A Sparse Coding Interpretation of Neural Networks and Theoretical Implications
• Customizing First Person Image Through Desired Actions
• Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs
• Parallelized Reverse Curriculum Generation
• SynFace: Face Recognition with Synthetic Data
• Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition
• From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research
• Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GAN
• Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks
• High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss
• Gaussian Filter in CRF Based Semantic Segmentation
• Towards Design Methodology of Efficient Fast Algorithms for Accelerating Generative Adversarial Networks on FPGAs
• Human Annotations Improve GAN Performances
• DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
• A Survey on Adversarial Image Synthesis
• Pixel-wise Conditioning of Generative Adversarial Networks
• CerfGAN: A Compact, Effective, Robust, and Fast Model for Unsupervised Multi-Domain Image-to-Image Translation
• Generative Adversarial Networks with Inverse Transformation Unit
• Representation Learning in Partially Observable Environments using Sensorimotor Prediction
• Distributed Generative Adversarial Net
• Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
• AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework
• Semantic and Geometric Unfolding of StyleGAN Latent Space
• Batch Face Alignment using a Low-rank GAN
• A Self-Training Method for Semi-Supervised GANs
• Segmentation of Objects by Hashing
• Approximating Probability Distributions by using Wasserstein Generative Adversarial Networks
• Resisting Large Data Variations via Introspective Transformation Network
• Differentiable probabilistic programming for strong gravitational lensing
• Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks
• N2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patients
• Fine-scale Surface Normal Estimation using a Single NIR Image
• Unconstrained Road Marking Recognition with Generative Adversarial Networks
• Autonomously and Simultaneously Refining Deep Neural Network Parameters by Generative Adversarial Networks
• KGAN: How to Break The Minimax Game in GAN
• Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
• Shape related constraints aware generation of Mechanical Designs through Deep Convolutional GAN
• Reparameterized Sampling for Generative Adversarial Networks
• Pseudo-positive regularization for deep person re-identification
• CNN-based Semantic Segmentation using Level Set Loss
• Generating a Fusion Image: One's Identity and Another's Shape
• Understanding the Role of Adversarial Regularization in Supervised Learning
• On Latent Distributions Without Finite Mean in Generative Models
• Recognition and Synthesis of Object Transport Motion
• Improving Protein Gamma-Turn Prediction Using Inception Capsule Networks
• Representation Learning from Limited Educational Data with Crowdsourced Labels
• CSI2Image: Image Reconstruction from Channel State Information Using Generative Adversarial Networks
• High Diversity Attribute Guided Face Generation with GANs
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• Learned Interpolation for 3D Generation
• Dual-discriminator GAN: A GAN way of profile face recognition
• Line Art Correlation Matching Feature Transfer Network for Automatic Animation Colorization
• Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
• Adversarial Code Learning for Image Generation
• Class Balancing GAN with a Classifier in the Loop
• Towards Stable Imbalanced Data Classification via Virtual Big Data Projection
• GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation
• Vehicle Image Generation Going Well with The Surroundings
• Image Semantic Transformation: Faster, Lighter and Stronger
• Joint Deep Learning of Facial Expression Synthesis and Recognition
• Spherical Feature Transform for Deep Metric Learning
• Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation
• Discovering Interesting Plots in Production Yield Data Analytics
• Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation
• Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
• WAYLA - Generating Images from Eye Movements
• The Benefits of Pairwise Discriminators for Adversarial Training
• Learning to Inpaint by Progressively Growing the Mask Regions
• Improving Generative Adversarial Networks with Local Coordinate Coding
• Generative Adversarial Network: Some Analytical Perspectives
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis