Improved Techniques for Training GANs

Abstract

We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic. Unlike most work on generative models, our primary goal is not to train a model that assigns high likelihood to test data, nor do we require the model to be able to learn well without using any labels. Using our new techniques, we achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN. The generated images are of high quality as confirmed by a visual Turing test: our model generates MNIST samples that humans cannot distinguish from real data, and CIFAR-10 samples that yield a human error rate of 21.3%. We also present ImageNet samples with unprecedented resolution and show that our methods enable the model to learn recognizable features of ImageNet classes.

Cited by in corpus (495)

• Generative Adversarial Networks: An Overview
• Spectral Normalization for Generative Adversarial Networks
• ICLabel: An automated electroencephalographic independent component classifier, dataset, and website
• Diffusion Models Beat GANs on Image Synthesis
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Temporal Ensembling for Semi-Supervised Learning
• Improved Training of Wasserstein GANs
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Training Generative Adversarial Networks with Limited Data
• Deep learning for molecular design - a review of the state of the art
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Pose Guided Person Image Generation
• Invertible Conditional GANs for image editing
• The relativistic discriminator: a key element missing from standard GAN
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Quantum machine learning: a classical perspective
• Unsupervised Image-to-Image Translation Networks
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• MolGAN: An implicit generative model for small molecular graphs
• Generating Natural Adversarial Examples
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• cGANs with Projection Discriminator
• Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
• C-RNN-GAN: Continuous recurrent neural networks with adversarial training
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Towards Principled Methods for Training Generative Adversarial Networks
• Scalable Private Learning with PATE
• Differentially Private Generative Adversarial Network
• MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• BAGAN: Data Augmentation with Balancing GAN
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
• Good Semi-supervised Learning that Requires a Bad GAN
• Triple Generative Adversarial Nets
• An empirical study on evaluation metrics of generative adversarial networks
• A Note on the Inception Score
• Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
• Generative Image Inpainting with Contextual Attention
• Synthesizing Tabular Data using Generative Adversarial Networks
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Deep Voice 2: Multi-Speaker Neural Text-to-Speech
• Few-Shot Adversarial Domain Adaptation
• A General Framework for Adversarial Examples with Objectives
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• The Numerics of GANs
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
• Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Least Squares Generative Adversarial Networks
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Generating Handwritten Chinese Characters using CycleGAN
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
• Sharp Minima Can Generalize For Deep Nets
• On the regularization of Wasserstein GANs
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
• Adversarial Feature Matching for Text Generation
• Dual Discriminator Generative Adversarial Nets
• Scalable agent alignment via reward modeling: a research direction
• Learning to Protect Communications with Adversarial Neural Cryptography
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• A Survey on GANs for Anomaly Detection
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• Recent Advances in Deep Learning: An Overview
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
• Real-Time Adaptive Image Compression
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
• ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?
• Skin Lesion Synthesis with Generative Adversarial Networks
• The Unusual Effectiveness of Averaging in GAN Training
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• On the Origin of Deep Learning
• Fashion-Gen: The Generative Fashion Dataset and Challenge
• GP-GAN: Towards Realistic High-Resolution Image Blending
• Unfolding with Generative Adversarial Networks
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• Learning Plannable Representations with Causal InfoGAN
• Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
• Generative Adversarial Residual Pairwise Networks for One Shot Learning
• Photographic Image Synthesis with Cascaded Refinement Networks
• ChatPainter: Improving Text to Image Generation using Dialogue
• Triangle Generative Adversarial Networks
• FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
• Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks
• Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network
• A-NICE-MC: Adversarial Training for MCMC
• Adversarial Neural Machine Translation
• Stabilizing GAN Training with Multiple Random Projections
• Variational Inference using Implicit Distributions
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
• Detecting GAN-generated Imagery using Color Cues
• Low-Shot Learning from Imaginary Data
• Adversarial Evaluation of Dialogue Models
• Cross-view image synthesis using geometry-guided conditional GANs
• Geometry Score: A Method For Comparing Generative Adversarial Networks
• Stabilizing Generative Adversarial Networks: A Survey
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions
• FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Self-ensembling for visual domain adaptation
• Implicit Maximum Likelihood Estimation
• DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification
• Generative OpenMax for Multi-Class Open Set Classification
• MAGAN: Margin Adaptation for Generative Adversarial Networks
• A Novel Topology Optimization Approach using Conditional Deep Learning
• Multi-Generator Generative Adversarial Nets
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Adversarial Dropout Regularization
• ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
• Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation
• Machine Learning for Physics-Informed Generation of Dispersed Multiphase Flow Using Generative Adversarial Networks
• Be Your Own Prada: Fashion Synthesis with Structural Coherence
• Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
• Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
• Activation Maximization Generative Adversarial Nets
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• A Topology Layer for Machine Learning
• Unsupervised Text Style Transfer using Language Models as Discriminators
• Stacked Generative Adversarial Networks
• Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
• Learning Approximate Inference Networks for Structured Prediction
• Addressing Overfitting on Pointcloud Classification using Atrous XCRF
• Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
• Convergence Problems with Generative Adversarial Networks (GANs)
• Improving GANs Using Optimal Transport
• Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
• Multi-View Image Generation from a Single-View
• Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis
• AGAN: Towards Automated Design of Generative Adversarial Networks
• Megapixel Size Image Creation using Generative Adversarial Networks
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
• Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
• Generative Adversarial Network Training is a Continual Learning Problem
• PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics
• ZhuSuan: A Library for Bayesian Deep Learning
• Unifying Multimodal Transformer for Bi-directional Image and Text Generation
• GANs for generating EFT models
• Bipartite Graph Reasoning GANs for Person Image Generation
• Adversarial Symmetric Variational Autoencoder
• Novelty Detection with GAN
• Lower Dimensional Kernels for Video Discriminators
• Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
• Temporal Generative Adversarial Nets with Singular Value Clipping
• MAGAN: Aligning Biological Manifolds
• Safer Classification by Synthesis
• A Tutorial on Deep Latent Variable Models of Natural Language
• Are generative deep models for novelty detection truly better?
• Creativity: Generating Diverse Questions using Variational Autoencoders
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• Text to Image Synthesis Using Generative Adversarial Networks
• Adversarial Learning with Local Coordinate Coding
• Autoregressive Quantile Networks for Generative Modeling
• Class-Splitting Generative Adversarial Networks
• Airline Passenger Name Record Generation using Generative Adversarial Networks
• Adversarial Distillation of Bayesian Neural Network Posteriors
• Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
• Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
• On the Benefit of Adversarial Training for Monocular Depth Estimation
• Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• AutoLoss: Learning Discrete Schedules for Alternate Optimization
• Improved Training of Generative Adversarial Networks Using Representative Features
• A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks
• Toward Diverse Text Generation with Inverse Reinforcement Learning
• CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
• Improved Consistency Regularization for GANs
• Deep Co-Training for Semi-Supervised Image Recognition
• Diversified Texture Synthesis with Feed-forward Networks
• GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning
• Generative Modeling with Conditional Autoencoders: Building an Integrated Cell
• Structured Generative Adversarial Networks
• Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
• McGan: Mean and Covariance Feature Matching GAN
• Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records
• SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation
• Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
• Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
• Cross-Domain Few-Shot Learning by Representation Fusion
• Adversarial Time-to-Event Modeling
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Inverting The Generator Of A Generative Adversarial Network (II)
• FCC-GAN: A Fully Connected and Convolutional Net Architecture for GANs
• Skill Rating for Generative Models
• MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
• Unsupervised Neural Domain Adaptation for Document Image Binarization
• Learning Uncertain Convolutional Features for Accurate Saliency Detection
• Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
• Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• Mode Collapse and Regularity of Optimal Transportation Maps
• TF-Replicator: Distributed Machine Learning for Researchers
• Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
• Invisible Steganography via Generative Adversarial Networks
• M2E-Try On Net: Fashion from Model to Everyone
• AC-BLSTM: Asymmetric Convolutional Bidirectional LSTM Networks for Text Classification
• An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
• Semi-Supervised Sequence Modeling with Cross-View Training
• Exploring the Evolution of GANs through Quality Diversity
• Towards Robust Neural Machine Translation
• Towards a Better Understanding and Regularization of GAN Training Dynamics
• Load Balanced GANs for Multi-view Face Image Synthesis
• eCommerceGAN : A Generative Adversarial Network for E-commerce
• An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• SPEED: Secure, PrivatE, and Efficient Deep learning
• GANGs: Generative Adversarial Network Games
• Unsupervised Person Image Synthesis in Arbitrary Poses
• Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds
• Symmetric Variational Autoencoder and Connections to Adversarial Learning
• Semi-supervised Rare Disease Detection Using Generative Adversarial Network
• Generative Adversarial Network for Handwritten Text
• Tensorial Mixture Models
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• Learning Face Age Progression: A Pyramid Architecture of GANs
• On the Effectiveness of Least Squares Generative Adversarial Networks
• $c^{+}$GAN: Complementary Fashion Item Recommendation
• Efficient GAN-based method for cyber-intrusion detection
• Every Smile is Unique: Landmark-Guided Diverse Smile Generation
• Training on the test set? An analysis of Spampinato et al. [31]
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• A Probabilistic Framework for Deep Learning
• Learning to Sketch with Shortcut Cycle Consistency
• DOOM Level Generation using Generative Adversarial Networks
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
• Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
• Packet-Level Adversarial Network Traffic Crafting using Sequence Generative Adversarial Networks
• Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
• Measuring the Transferability of Adversarial Examples
• AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
• Projection Based Weight Normalization for Deep Neural Networks
• Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
• Prediction Under Uncertainty with Error-Encoding Networks
• Quantitatively Evaluating GANs With Divergences Proposed for Training
• From source to target and back: symmetric bi-directional adaptive GAN
• Reposing Humans by Warping 3D Features
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis
• Combinets: Creativity via Recombination of Neural Networks
• Semi-parametric Image Inpainting
• Spectral Regularization for Combating Mode Collapse in GANs
• Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
• LOGAN: Membership Inference Attacks Against Generative Models
• TequilaGAN: How to easily identify GAN samples
• Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
• DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• Composite Functional Gradient Learning of Generative Adversarial Models
• IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
• Game of Learning Bloch Equation Simulations for MR Fingerprinting
• A New CGAN Technique for Constrained Topology Design Optimization
• RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
• Question-Conditioned Counterfactual Image Generation for VQA
• Unbiased Auxiliary Classifier GANs with MINE
• One-Class Adversarial Nets for Fraud Detection
• Interactive Image Manipulation with Natural Language Instruction Commands
• Semantically Consistent Image Completion with Fine-grained Details
• Optimal transport maps for distribution preserving operations on latent spaces of Generative Models
• Semi-Supervised Learning using Siamese Networks
• Fluid Flow Mass Transport for Generative Networks
• Improved Training with Curriculum GANs
• Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
• GILT: Generating Images from Long Text
• Learning the Base Distribution in Implicit Generative Models
• Likelihood Estimation for Generative Adversarial Networks
• Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
• DeadNet: Identifying Phototoxicity from Label-free Microscopy Images of Cells using Deep ConvNets
• Annealed Generative Adversarial Networks
• Some Theoretical Properties of GANs
• Maximum Mutation Reinforcement Learning for Scalable Control
• Self-Supervised Feature Learning by Learning to Spot Artifacts
• EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
• GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
• (q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs
• A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
• Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
• TripletGAN: Training Generative Model with Triplet Loss
• Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
• Regularizing by the Variance of the Activations' Sample-Variances
• Generating Synthetic Multispectral Satellite Imagery from Sentinel-2
• Cross-Modal Retrieval with Implicit Concept Association
• Generalization and Memorization: The Bias Potential Model
• Unsupervised Single Image Deraining with Self-supervised Constraints
• Mini-batch graphs for robust image classification
• Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
• 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
• Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach
• Generating Text Sequence Images for Recognition
• Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
• Recent Advances of Image Steganography with Generative Adversarial Networks
• Disentangling and Learning Robust Representations with Natural Clustering
• General-to-Detailed GAN for Infrequent Class Medical Images
• Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks
• Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks
• Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
• Chinese Typeface Transformation with Hierarchical Adversarial Network
• GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
• A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
• Recapture as You Want
• Deep Cross-Modal Audio-Visual Generation
• Learning the Precise Feature for Cluster Assignment
• What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks
• Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks
• Semantic Explanations of Predictions
• Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images
• Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
• Decoupled Learning for Conditional Adversarial Networks
• Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
• Metric Learning-based Generative Adversarial Network
• Image-derived generative modeling of pseudo-macromolecular structures - towards the statistical assessment of Electron CryoTomography template matching
• GANs beyond divergence minimization
• Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification
• PixelCNN Models with Auxiliary Variables for Natural Image Modeling
• MR-GAN: Manifold Regularized Generative Adversarial Networks
• InverseNet: Solving Inverse Problems with Splitting Networks
• Performing Co-Membership Attacks Against Deep Generative Models
• BIM Hyperreality: Data Synthesis Using BIM and Hyperrealistic Rendering for Deep Learning
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• A Wasserstein GAN model with the total variational regularization
• Learning to Synthesize Fashion Textures
• Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization
• WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks
• Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
• Shape Generation using Spatially Partitioned Point Clouds
• Hybrid VAE: Improving Deep Generative Models using Partial Observations
• A Plug-in Method for Representation Factorization in Connectionist Models
• Chemical Structure Elucidation from Mass Spectrometry by Matching Substructures
• Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning
• Spatial PixelCNN: Generating Images from Patches
• CRAFT: Complementary Recommendations Using Adversarial Feature Transformer
• First Order Generative Adversarial Networks
• Supervised Adversarial Networks for Image Saliency Detection
• Manifold Adversarial Learning
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Deep Generative Learning via Variational Gradient Flow
• Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
• Score-Guided Generative Adversarial Networks
• Predicting Opioid Relapse Using Social Media Data
• MMGAN: Manifold Matching Generative Adversarial Network
• Learning Continuous Face Age Progression: A Pyramid of GANs
• C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis
• Customizing an Adversarial Example Generator with Class-Conditional GANs
• Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion
• Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks
• Disentangling Content and Style via Unsupervised Geometry Distillation
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
• Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip Connections
• ByteSGAN: A Semi-supervised Generative Adversarial Network for Encrypted Traffic Classification of SDN Edge Gateway in Green Communication Network
• A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
• Model Extraction and Defenses on Generative Adversarial Networks
• Synthesizing Diverse, High-Quality Audio Textures
• AutoGAN: Robust Classifier Against Adversarial Attacks
• Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
• Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
• Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging
• Towards Audio to Scene Image Synthesis using Generative Adversarial Network
• Adversarial Transformations for Semi-Supervised Learning
• Mean Shift Rejection: Training Deep Neural Networks Without Minibatch Statistics or Normalization
• CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
• Backpropagation for Implicit Spectral Densities
• Adversarial Constraint Learning for Structured Prediction
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• Semi-supervised classification by reaching consensus among modalities
• Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
• Decomposed Adversarial Learned Inference
• Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos
• Modeling EEG data distribution with a Wasserstein Generative Adversarial Network to predict RSVP Events
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• Adversarial Pixel-Level Generation of Semantic Images
• Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRI
• Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models
• MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones
• Imitation Learning with Sinkhorn Distances
• Generative Adversarial Mapping Networks
• Cycle-Consistent Inverse GAN for Text-to-Image Synthesis
• Pairwise Augmented GANs with Adversarial Reconstruction Loss
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
• Adversarially Learned Mixture Model
• A coevolutionary approach to deep multi-agent reinforcement learning
• Collaborative Sampling in Generative Adversarial Networks
• Learning Controllable Disentangled Representations with Decorrelation Regularization
• Max-Margin Deep Generative Models for (Semi-)Supervised Learning
• Facial Information Recovery from Heavily Damaged Images using Generative Adversarial Network- PART 1
• A Generative Model for Hallucinating Diverse Versions of Super Resolution Images
• Disentangling Pose from Appearance in Monochrome Hand Images
• Stable Distribution Alignment Using the Dual of the Adversarial Distance
• Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
• Deep Consensus Learning
• Low-Shot Learning for the Semantic Segmentation of Remote Sensing Imagery
• Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
• Channel-Recurrent Autoencoding for Image Modeling
• Generalized Latent Variable Recovery for Generative Adversarial Networks
• A Novel Framework for Selection of GANs for an Application
• Applying Generative Adversarial Networks to Intelligent Subsurface Imaging and Identification
• HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning
• Curriculum Learning for Deep Generative Models with Clustering
• Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning
• Joint Learning of Neural Networks via Iterative Reweighted Least Squares
• Fréchet ChemNet Distance: A metric for generative models for molecules in drug discovery
• Semi-Supervised Learning via New Deep Network Inversion
• MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
• Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning
• Memory-guided Unsupervised Image-to-image Translation
• A Study into the similarity in generator and discriminator in GAN architecture
• Towards Deeper Generative Architectures for GANs using Dense connections
• G3AN: Disentangling Appearance and Motion for Video Generation
• Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
• Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation
• ROI Regularization for Semi-supervised and Supervised Learning
• Fine-grained Image-to-Image Transformation towards Visual Recognition
• Less Memory, Faster Speed: Refining Self-Attention Module for Image Reconstruction
• DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network
• Out-of-Sample Testing for GANs
• Student's t-Generative Adversarial Networks
• Generative Creativity: Adversarial Learning for Bionic Design
• Adversarial Training of Word2Vec for Basket Completion
• Radio Galaxy Morphology Generation Using DNN Autoencoder and Gaussian Mixture Models
• Restricting Greed in Training of Generative Adversarial Network
• Wasserstein Introspective Neural Networks
• Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
• Combining Attention with Flow for Person Image Synthesis
• Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
• Autonomous Learning of Features for Control: Experiments with Embodied and Situated Agents
• Geometric Enclosing Networks
• LoGAN: Generating Logos with a Generative Adversarial Neural Network Conditioned on color
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
• Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning
• PortraitGAN for Flexible Portrait Manipulation
• Image Manipulation with Natural Language using Two-sidedAttentive Conditional Generative Adversarial Network
• Text-to-image Synthesis via Symmetrical Distillation Networks
• A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients
• Towards Robust Pattern Recognition: A Review
• A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation
• Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text
• MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network
• Unrealistic Feature Suppression for Generative Adversarial Networks
• A Layer-Based Sequential Framework for Scene Generation with GANs
• A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
• Maximal Information Leakage based Privacy Preserving Data Disclosure Mechanisms
• Virtual Conditional Generative Adversarial Networks
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• CIGLI: Conditional Image Generation from Language & Image
• DINO: A Conditional Energy-Based GAN for Domain Translation
• Attending Category Disentangled Global Context for Image Classification
• MOC-GAN: Mixing Objects and Captions to Generate Realistic Images
• Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
• Diversity Regularized Adversarial Learning
• Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy
• Regularizing Deep Hashing Networks Using GAN Generated Fake Images
• Escaping from Collapsing Modes in a Constrained Space
• Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
• Conditioning of Reinforcement Learning Agents and its Policy Regularization Application
• HAD-GAN: A Human-perception Auxiliary Defense GAN to Defend Adversarial Examples
• Image Manipulation with Perceptual Discriminators
• Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems
• Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks
• Improved Training for Self-Training by Confidence Assessments
• Parameter Reference Loss for Unsupervised Domain Adaptation
• Adversarial Training Methods for Network Embedding
• ErGAN: Generative Adversarial Networks for Entity Resolution
• Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
• FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection
• Generating Contradictory, Neutral, and Entailing Sentences
• Forget the Learning Rate, Decay Loss
• Synthetic-to-Real Domain Adaptation for Lane Detection
• Task-Assisted Domain Adaptation with Anchor Tasks
• The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems
• Generative Adversarial Nets for Multiple Text Corpora
• Deep Convolutional Generative Adversarial Network Based Food Recognition Using Partially Labeled Data
• Imitation with Neural Density Models
• On the Limits of Learning Representations with Label-Based Supervision
• Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction
• A Self-Training Method for Semi-Supervised GANs
• PCGAN: Partition-Controlled Human Image Generation
• MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
• Local Stability and Performance of Simple Gradient Penalty mu-Wasserstein GAN