Spectral Normalization for Generative Adversarial Networks

Abstract

One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques.

Published as a conference paper at ICLR 2018

References in corpus (14)

• Conditional Generative Adversarial Nets
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Generative Adversarial Imitation Learning
• Neural Photo Editing with Introspective Adversarial Networks
• Spectral Norm Regularization for Improving the Generalizability of Deep Learning
• Adversarial Learning for Neural Dialogue Generation
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
• On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
• Generative Adversarial Nets from a Density Ratio Estimation Perspective

Cited by in corpus (701)

• Denoising Diffusion Probabilistic Models
• Generative Adversarial Network in Medical Imaging: A Review
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Generative Modeling by Estimating Gradients of the Data Distribution
• Training Generative Adversarial Networks with Limited Data
• HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
• Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study
• The relativistic discriminator: a key element missing from standard GAN
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• Deep Learning for Deepfakes Creation and Detection: A Survey
• cGANs with Projection Discriminator
• Perceptual Adversarial Networks for Image-to-Image Transformation
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
• Large Scale Adversarial Representation Learning
• How Generative Adversarial Networks and Their Variants Work: An Overview
• NVAE: A Deep Hierarchical Variational Autoencoder
• Normalizing Flows for Probabilistic Modeling and Inference
• GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
• Improved Precision and Recall Metric for Assessing Generative Models
• Neural Lander: Stable Drone Landing Control using Learned Dynamics
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• MOPO: Model-based Offline Policy Optimization
• Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
• HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions
• High-Fidelity Generative Image Compression
• Stochastic Adversarial Video Prediction
• Leveraging Frequency Analysis for Deep Fake Image Recognition
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• Invertible Residual Networks
• A Variational Inequality Perspective on Generative Adversarial Networks
• Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring
• Adversarial Video Generation on Complex Datasets
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• Improved Techniques for Training Score-Based Generative Models
• Lipschitz regularity of deep neural networks: analysis and efficient estimation
• Optimization for deep learning: theory and algorithms
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
• Video-to-Video Synthesis
• Banach Wasserstein GAN
• PEPSI++: Fast and Lightweight Network for Image Inpainting
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• A survey on GANs for computer vision: Recent research, analysis and taxonomy
• Review: Deep Learning in Electron Microscopy
• From Variational to Deterministic Autoencoders
• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
• The Unusual Effectiveness of Averaging in GAN Training
• InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
• Differentiable Augmentation for Data-Efficient GAN Training
• Implicit Generation and Generalization in Energy-Based Models
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
• Image Synthesis with a Single (Robust) Classifier
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• Deep Polynomial Neural Networks
• SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network
• Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Quality
• Few-Shot Unsupervised Image-to-Image Translation
• ViTGAN: Training GANs with Vision Transformers
• ChatPainter: Improving Text to Image Generation using Dialogue
• Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
• Interpreting the Latent Space of GANs for Semantic Face Editing
• Deep Learning for Image Super-resolution: A Survey
• On Self Modulation for Generative Adversarial Networks
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Wavelet-Packets for Deepfake Image Analysis and Detection
• Learning quantum data with the quantum Earth Mover's distance
• Wasserstein GANs for MR Imaging: from Paired to Unpaired Training
• DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
• Collaborative Learning for Faster StyleGAN Embedding
• Sorting out Lipschitz function approximation
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Robust Differentiable SVD
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching
• A Systematic Survey of Regularization and Normalization in GANs
• Maximum Entropy Generators for Energy-Based Models
• When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark
• Unsupervised Object Segmentation by Redrawing
• Improved StyleGAN Embedding: Where are the Good Latents?
• T-former: An Efficient Transformer for Image Inpainting
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• StructureFlow: Image Inpainting via Structure-aware Appearance Flow
• Reducing Noise in GAN Training with Variance Reduced Extragradient
• On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
• SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors
• On Leveraging Pretrained GANs for Generation with Limited Data
• Efficient texture-aware multi-GAN for image inpainting
• Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution
• ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
• LOGAN: Latent Optimisation for Generative Adversarial Networks
• Few-Shot Adaptation of Generative Adversarial Networks
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
• On gradient regularizers for MMD GANs
• Is Attention Better Than Matrix Decomposition?
• Learnable Gated Temporal Shift Module for Deep Video Inpainting
• An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey
• Parseval Proximal Neural Networks
• Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
• Is Generator Conditioning Causally Related to GAN Performance?
• MTRNet++: One-stage Mask-based Scene Text Eraser
• Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
• Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
• VCGAN: Video Colorization with Hybrid Generative Adversarial Network
• MDA GAN: Adversarial-Learning-based 3-D Seismic Data Interpolation and Reconstruction for Complex Missing
• PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
• DECAF: Deep Extreme Classification with Label Features
• Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
• Rethinking Monocular Depth Estimation with Adversarial Training
• Adversarially Regularized Autoencoders
• SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
• Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images
• NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations
• Understanding GANs: the LQG Setting
• Quaternion Generative Adversarial Networks
• RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
• Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising
• Lower Dimensional Kernels for Video Discriminators
• Boundless: Generative Adversarial Networks for Image Extension
• A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
• Cross-Modal Contrastive Learning for Text-to-Image Generation
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• End-to-End Adversarial Text-to-Speech
• Investigating Object Compositionality in Generative Adversarial Networks
• Small-GAN: Speeding Up GAN Training Using Core-sets
• Learning to Optimize Domain Specific Normalization for Domain Generalization
• A Tutorial on Deep Latent Variable Models of Natural Language
• Spatially Controllable Image Synthesis with Internal Representation Collaging
• Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
• InGAN: Capturing and Remapping the "DNA" of a Natural Image
• Biosignal Generation and Latent Variable Analysis with Recurrent Generative Adversarial Networks
• On the Evaluation of Conditional GANs
• A Large-Scale Study on Regularization and Normalization in GANs
• Rapid tissue oxygenation mapping from snapshot structured-light images with adversarial deep learning
• A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
• ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis
• Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Simple yet Effective Way for Improving the Performance of GAN
• Adversarial score matching and improved sampling for image generation
• Learning to Defend by Learning to Attack
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• Focal Frequency Loss for Image Reconstruction and Synthesis
• Globally-Robust Neural Networks
• Convolutional Generation of Textured 3D Meshes
• Sketch-based Creativity Support Tools using Deep Learning
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• The Lipschitz Constant of Self-Attention
• Physics-informed GANs for Coastal Flood Visualization
• Feature Quantization Improves GAN Training
• Visual Intelligence through Human Interaction
• Improved Contrastive Divergence Training of Energy Based Models
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
• Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
• SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking
• Unsupervised Adversarial Correction of Rigid MR Motion Artifacts
• Improved Consistency Regularization for GANs
• Deep Image Spatial Transformation for Person Image Generation
• Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
• Approximation Capabilities of Neural ODEs and Invertible Residual Networks
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• GANs May Have No Nash Equilibria
• MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement
• Lipschitz regularized Deep Neural Networks generalize and are adversarially robust
• Unsupervised Domain Adaptation for Semantic Segmentation using One-shot Image-to-Image Translation via Latent Representation Mixing
• Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning
• Cross-domain Correspondence Learning for Exemplar-based Image Translation
• MetroGAN: Simulating Urban Morphology with Generative Adversarial Network
• Photo-Realistic Video Prediction on Natural Videos of Largely Changing Frames
• NU-GAN: High resolution neural upsampling with GAN
• Adversarially Learned Anomaly Detection
• Semi-supervised Image Attribute Editing using Generative Adversarial Networks
• RED: A ReRAM-based Deconvolution Accelerator
• Foreground-aware Image Inpainting
• Improved robustness to adversarial examples using Lipschitz regularization of the loss
• Robust Estimation and Generative Adversarial Nets
• Generative Adversarial Networks Applied to Synthetic Financial Scenarios Generation
• DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
• Hybrid Discriminative-Generative Training via Contrastive Learning
• Image inpainting using frequency domain priors
• GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
• Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Human-Like Sketches
• Task-Relevant Adversarial Imitation Learning
• Decompose to manipulate: Manipulable Object Synthesis in 3D Medical Images with Structured Image Decomposition
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
• Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition
• Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
• TF-Replicator: Distributed Machine Learning for Researchers
• Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
• Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
• Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
• Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
• Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
• A Spectral Energy Distance for Parallel Speech Synthesis
• Responsible Disclosure of Generative Models Using Scalable Fingerprinting
• Image Inpainting via Conditional Texture and Structure Dual Generation
• 3D Photography using Context-aware Layered Depth Inpainting
• Exploring the Evolution of GANs through Quality Diversity
• DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images
• Image-to-Image Translation: Methods and Applications
• LaFIn: Generative Landmark Guided Face Inpainting
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• Meta-Adaptive Nonlinear Control: Theory and Algorithms
• Adversarial Lipschitz Regularization
• Towards a Better Understanding and Regularization of GAN Training Dynamics
• Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
• What Matters for Adversarial Imitation Learning?
• Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
• CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
• Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
• Generative Latent Flow
• Mimicry: Towards the Reproducibility of GAN Research
• A Spectral Regularizer for Unsupervised Disentanglement
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• Learning Deep Features in Instrumental Variable Regression
• Semialgebraic Optimization for Lipschitz Constants of ReLU Networks
• Some Theoretical Insights into Wasserstein GANs
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
• On the distance between two neural networks and the stability of learning
• Diving Deeper into Underwater Image Enhancement: A Survey
• Map completion from partial observation using the global structure of multiple environmental maps
• A case for new neural network smoothness constraints
• PowerNorm: Rethinking Batch Normalization in Transformers
• Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems
• A Deep Learning Framework to Reconstruct Face under Mask
• Robust learning with implicit residual networks
• Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses
• Negative Momentum for Improved Game Dynamics
• Synthesizing lesions using contextual GANs improves breast cancer classification on mammograms
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis
• PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design
• Image Generation From Small Datasets via Batch Statistics Adaptation
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• SALSA-TEXT : self attentive latent space based adversarial text generation
• Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Implicit competitive regularization in GANs
• Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
• Efficient Generation of Structured Objects with Constrained Adversarial Networks
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
• PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
• Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
• Generative Low-bitwidth Data Free Quantization
• Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?
• Wasserstein Distance Based Domain Adaptation for Object Detection
• Triple consistency loss for pairing distributions in GAN-based face synthesis
• Perceptual Generative Autoencoders
• Progressive Semantic-Aware Style Transformation for Blind Face Restoration
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
• GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling
• Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing
• On Training Implicit Models
• UGAN: Untraceable GAN for Multi-Domain Face Translation
• DeViT: Deformed Vision Transformers in Video Inpainting
• Transformation-based Adversarial Video Prediction on Large-Scale Data
• Generative Models as Distributions of Functions
• Continual Learning in Recurrent Neural Networks
• GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
• Effect of The Latent Structure on Clustering with GANs
• AdversarialNAS: Adversarial Neural Architecture Search for GANs
• Exponential Family Estimation via Adversarial Dynamics Embedding
• Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
• Anisotropic Stroke Control for Multiple Artists Style Transfer
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations
• AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
• Competitive Training of Mixtures of Independent Deep Generative Models
• Hierarchical Opacity Propagation for Image Matting
• Spectral Regularization for Combating Mode Collapse in GANs
• Parallel Scheduled Sampling
• Inspector Gadget: A Data Programming-based Labeling System for Industrial Images
• SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images
• Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
• Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective
• Surprising Negative Results for Generative Adversarial Tree Search
• Generating unrepresented proportions of geological facies using Generative Adversarial Networks
• Behavior From the Void: Unsupervised Active Pre-Training
• MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation
• From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent
• cGANs with Multi-Hinge Loss
• Extended Batch Normalization
• Training Deep Energy-Based Models with f-Divergence Minimization
• LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
• Newton-type Methods for Minimax Optimization
• Does Knowledge Distillation Really Work?
• Globally Injective ReLU Networks
• Generative Convolution Layer for Image Generation
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• A Comprehensive Review of Deep Learning-based Single Image Super-resolution
• ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
• Invertible DenseNets with Concatenated LipSwish
• PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain
• Using deep generative neural networks to account for model errors in Markov chain Monte Carlo inversion
• Realistic Ultrasound Image Synthesis for Improved Classification of Liver Disease
• COCO-GAN: Generation by Parts via Conditional Coordinating
• Categorical Perception: A Groundwork for Deep Learning
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
• Deep Exemplar-based Video Colorization
• Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
• Training Generative Adversarial Networks Via Turing Test
• Learning disconnected manifolds: a no GANs land
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
• PolyGAN: High-Order Polynomial Generators
• Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN
• The Devil is in the Decoder: Classification, Regression and GANs
• FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
• How does Lipschitz Regularization Influence GAN Training?
• High Fidelity Face Manipulation with Extreme Poses and Expressions
• Robust and Provably Monotonic Networks
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
• Few-shot Neural Architecture Search
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
• Twin Auxiliary Classifiers GAN
• Causal Influence Detection for Improving Efficiency in Reinforcement Learning
• FIRe-GAN: A novel Deep Learning-based infrared-visible fusion method for wildfire imagery
• Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
• Designing Stable Neural Networks using Convex Analysis and ODEs
• Triple Generative Adversarial Networks
• Group Equivariant Generative Adversarial Networks
• Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
• FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
• Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
• Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer
• Non-saturating GAN training as divergence minimization
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
• Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
• Tubular Shape Aware Data Generation for Semantic Segmentation in Medical Imaging
• GDPP: Learning Diverse Generations Using Determinantal Point Process
• Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
• GazeCorrection:Self-Guided Eye Manipulation in the wild using Self-Supervised Generative Adversarial Networks
• Positional Normalization
• Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
• SSN: Learning Sparse Switchable Normalization via SparsestMax
• In-Domain GAN Inversion for Real Image Editing
• CAGAN: Text-To-Image Generation with Combined Attention GANs
• CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
• When and How Can Deep Generative Models be Inverted?
• Robust Regression for Safe Exploration in Control
• Styleformer: Transformer based Generative Adversarial Networks with Style Vector
• Self-Supervised GANs with Label Augmentation
• KG-GAN: Knowledge-Guided Generative Adversarial Networks
• Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
• Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
• Teachers Do More Than Teach: Compressing Image-to-Image Models
• Image Synthesis From Reconfigurable Layout and Style
• Understanding and Stabilizing GANs' Training Dynamics with Control Theory
• Neural SDEs as Infinite-Dimensional GANs
• Self Sparse Generative Adversarial Networks
• High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
• $(f,\Gamma )$-Divergences: Interpolating between $f$-Divergences and Integral Probability Metrics
• Stable and expressive recurrent vision models
• Orthogonal Convolutional Neural Networks
• on the effectiveness of generative adversarial network on anomaly detection
• Fantastic Four: Differentiable Bounds on Singular Values of Convolution Layers
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models
• Image Generation from Layout
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• Learning the Precise Feature for Cluster Assignment
• Label-Noise Robust Generative Adversarial Networks
• Self-Supervised GANs via Auxiliary Rotation Loss
• On Scalable and Efficient Computation of Large Scale Optimal Transport
• Deep Line Art Video Colorization with a Few References
• JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels
• EigenGame: PCA as a Nash Equilibrium
• Decentralized Attribution of Generative Models
• Chunked Autoregressive GAN for Conditional Waveform Synthesis
• Discriminatory and orthogonal feature learning for noise robust keyword spotting
• Train simultaneously, generalize better: Stability of gradient-based minimax learners
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• StarSRGAN: Improving Real-World Blind Super-Resolution
• PAGAN: Portfolio Analysis with Generative Adversarial Networks
• Video Interpolation and Prediction with Unsupervised Landmarks
• Lipschitz Networks and Distributional Robustness
• Learning to Take Directions One Step at a Time
• Invertible residual networks in the context of regularization theory for linear inverse problems
• Model-Based Domain Generalization
• Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
• Open Event Extraction from Online Text using a Generative Adversarial Network
• Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
• Natural Image Matting via Guided Contextual Attention
• VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
• Learning Stochastic Behaviour from Aggregate Data
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
• Particle Cloud Generation with Message Passing Generative Adversarial Networks
• Robustness via Deep Low-Rank Representations
• Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
• cGANs with Conditional Convolution Layer
• CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
• On Relativistic $f$-Divergences
• End-to-End Conditional GAN-based Architectures for Image Colourisation
• Perceptually Motivated Method for Image Inpainting Comparison
• Channel Equilibrium Networks for Learning Deep Representation
• Distortion Agnostic Deep Watermarking
• Learning to Synthesize Fashion Textures
• Towards Understanding Normalization in Neural ODEs
• Attentive Normalization for Conditional Image Generation
• toon2real: Translating Cartoon Images to Realistic Images
• Discriminative-Generative Representation Learning for One-Class Anomaly Detection
• Generative Modeling with Optimal Transport Maps
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• GAN Cocktail: mixing GANs without dataset access
• Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives
• High Resolution Face Editing with Masked GAN Latent Code Optimization
• Dual Contrastive Loss and Attention for GANs
• Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks
• Learning by Turning: Neural Architecture Aware Optimisation
• Learning High Dimensional Wasserstein Geodesics
• Deep Learning-based Face Super-Resolution: A Survey
• How to GAN Event Unweighting
• Unsupervised Change Detection in Satellite Images with Generative Adversarial Network
• CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network
• Telescoping Density-Ratio Estimation
• An FPGA-Based On-Device Reinforcement Learning Approach using Online Sequential Learning
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment
• Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
• SeismoGen: Seismic Waveform Synthesis Using Generative Adversarial Networks
• An Acceleration Framework for High Resolution Image Synthesis
• Optimizing Through Learned Errors for Accurate Sports Field Registration
• Model Imitation for Model-Based Reinforcement Learning
• Potential Flow Generator with $L_2$ Optimal Transport Regularity for Generative Models
• Blind Deblurring Using GANs
• Generative Adversarial Networks for Unpaired Voice Transformation on Impaired Speech
• Learning towards Minimum Hyperspherical Energy
• Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks
• JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
• Time-domain Speech Enhancement with Generative Adversarial Learning
• Scalable Plug-and-Play ADMM with Convergence Guarantees
• Approximating Lipschitz continuous functions with GroupSort neural networks
• Taming GANs with Lookahead-Minmax
• MatchingGAN: Matching-based Few-shot Image Generation
• SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
• Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision
• Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation
• Flow Contrastive Estimation of Energy-Based Models
• Generating Embroidery Patterns Using Image-to-Image Translation
• TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search
• Taking Control of Intra-class Variation in Conditional GANs Under Weak Supervision
• Generalized Energy Based Models
• Murine AI excels at cats and cheese: Structural differences between human and mouse neurons and their implementation in generative AIs
• DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics
• Semantically Multi-modal Image Synthesis
• Selective Synthetic Augmentation with Quality Assurance
• Unsupervised Image Denoising with Frequency Domain Knowledge
• Variational Conditional GAN for Fine-grained Controllable Image Generation
• No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks
• Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
• GAN Memory with No Forgetting
• Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• PriorGAN: Real Data Prior for Generative Adversarial Nets
• Entropy-regularized Optimal Transport Generative Models
• DIFAI: Diverse Facial Inpainting using StyleGAN Inversion
• On Computation and Generalization of GANs with Spectrum Control
• Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
• Improved BiGAN training with marginal likelihood equalization
• Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination
• Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
• CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
• Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization
• To learn image super-resolution, use a GAN to learn how to do image degradation first
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• Towards Audio to Scene Image Synthesis using Generative Adversarial Network
• Decomposed Adversarial Learned Inference
• RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications
• Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?
• Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data
• Dual Adversarial Learning with Attention Mechanism for Fine-grained Medical Image Synthesis
• Boosting Image Outpainting with Semantic Layout Prediction
• A Temporally-Aware Interpolation Network for Video Frame Inpainting
• Latent Dirichlet Allocation in Generative Adversarial Networks
• SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization
• Class-Distinct and Class-Mutual Image Generation with GANs
• Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
• Adaptive Weighted Discriminator for Training Generative Adversarial Networks
• Refining Deep Generative Models via Discriminator Gradient Flow
• MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
• Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
• Neural Monge Map estimation and its applications
• Semi-supervised Learning for Few-shot Image-to-Image Translation
• MC-LSTM: Mass-Conserving LSTM
• Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
• Axial Residual Networks for CycleGAN-based Voice Conversion
• Synthetic Epileptic Brain Activities Using Generative Adversarial Networks
• Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision
• BalaGAN: Image Translation Between Imbalanced Domains via Cross-Modal Transfer
• Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators
• Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space
• Training Generative Adversarial Networks in One Stage
• A Frobenius norm regularization method for convolutional kernels to avoid unstable gradient problem
• Landmark Detection in Low Resolution Faces with Semi-Supervised Learning
• Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs
• Semi-supervised Learning using Adversarial Training with Good and Bad Samples
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
• The Convolution Exponential and Generalized Sylvester Flows
• F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
• Reciprocal Adversarial Learning via Characteristic Functions
• FIS-GAN: GAN with Flow-based Importance Sampling
• Efficient Super Resolution For Large-Scale Images Using Attentional GAN
• A Novel Framework for Selection of GANs for an Application
• A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
• Controllable Orthogonalization in Training DNNs
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
• Diverse Image Generation via Self-Conditioned GANs
• Adversarial Feature Desensitization
• Lessons Learned from the Training of GANs on Artificial Datasets
• Robust GANs against Dishonest Adversaries
• Alleviation of Gradient Exploding in GANs: Fake Can Be Real
• Learning Manifold Implicitly via Explicit Heat-Kernel Learning
• Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
• not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution
• Gradient penalty from a maximum margin perspective
• Latent Neural Differential Equations for Video Generation
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
• EigenGame Unloaded: When playing games is better than optimizing
• On the Existence of Optimal Transport Gradient for Learning Generative Models
• Exploring The Effect of High-frequency Components in GANs Training
• An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
• Incremental Concept Learning via Online Generative Memory Recall
• Continuous Face Aging via Self-estimated Residual Age Embedding
• Efficient and Accurate Gradients for Neural SDEs
• Iterated learning for emergent systematicity in VQA
• Towards Deeper Deep Reinforcement Learning with Spectral Normalization
• Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
• Curriculum Learning for Deep Generative Models with Clustering
• MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
• On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• DeDUCE: Generating Counterfactual Explanations Efficiently
• SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
• Guaranteed Trajectory Tracking under Learned Dynamics with Contraction Metrics and Disturbance Estimation
• Generative-Discriminative Complementary Learning
• General Probabilistic Surface Optimization and Log Density Estimation
• Transfer Learning with Pre-trained Conditional Generative Models
• Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
• Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesis
• Collaborative Sampling in Generative Adversarial Networks
• Inclusive normalization of face images to passport format
• Fast gradient-free activation maximization for neurons in spiking neural networks
• P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments
• Learning Segmentation Masks with the Independence Prior
• Continuous Facial Motion Deblurring
• Efficient acoustic feature transformation in mismatched environments using a Guided-GAN
• Cross-domain Imitation from Observations
• Learning View Priors for Single-view 3D Reconstruction
• Manifold-preserved GANs
• Pairwise Augmented GANs with Adversarial Reconstruction Loss
• ControlVAE: Tuning, Analytical Properties, and Performance Analysis
• Facial Emotion Recognition with Noisy Multi-task Annotations
• iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning
• Latent Space Optimal Transport for Generative Models
• Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
• How good is my GAN?
• Set Distribution Networks: a Generative Model for Sets of Images
• PoseGAN: A Pose-to-Image Translation Framework for Camera Localization
• Lipschitz Constrained GANs via Boundedness and Continuity
• Learning the Loss Functions in a Discriminative Space for Video Restoration
• Blur, Noise, and Compression Robust Generative Adversarial Networks
• What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes
• Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
• Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
• Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
• 3D Hand Pose Estimation via Regularized Graph Representation Learning
• Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder
• Generation of non-stationary stochastic fields using Generative Adversarial Networks
• CoPE: Conditional image generation using Polynomial Expansions
• Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation
• HRINet: Alternative Supervision Network for High-resolution CT image Interpolation
• Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
• KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling
• Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
• A Novel Measure to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images
• Semi-Anchored Multi-Step Gradient Descent Ascent Method for Structured Nonconvex-Nonconcave Composite Minimax Problems
• Autoencoding Under Normalization Constraints
• Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
• Less Memory, Faster Speed: Refining Self-Attention Module for Image Reconstruction
• A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients
• Rethinking Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics
• Convergent Graph Solvers
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• IQ-Learn: Inverse soft-Q Learning for Imitation
• IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
• Disentangling the Spatial Structure and Style in Conditional VAE
• Painting Outside as Inside: Edge Guided Image Outpainting via Bidirectional Rearrangement with Progressive Step Learning
• Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
• Guiding the One-to-one Mapping in CycleGAN via Optimal Transport
• G3AN: Disentangling Appearance and Motion for Video Generation
• Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching
• Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
• Quasi-Autoregressive Residual (QuAR) Flows
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• Conditioning Trick for Training Stable GANs
• Tessellated Wasserstein Auto-Encoders
• Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning
• Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
• Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent
• Making Method of Moments Great Again? -- How can GANs learn distributions
• Online Kernel based Generative Adversarial Networks
• Detecting Invasive Ductal Carcinoma with Semi-Supervised Conditional GANs
• From Rain Generation to Rain Removal
• Explicit Gradient Learning
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks
• Spectral Tensor Train Parameterization of Deep Learning Layers
• Multi-Metric Optimization using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement
• Improved Image Generation via Sparse Modeling
• Model-Aware Regularization For Learning Approaches To Inverse Problems
• Learning Camera-Aware Noise Models
• Nonparametric Online Learning Using Lipschitz Regularized Deep Neural Networks
• Label Geometry Aware Discriminator for Conditional Generative Networks
• Generative Adversarial Networks for Unsupervised Object Co-localization
• Input Invex Neural Network
• Generating Long-term Continuous Multi-type Generation Profiles
• Towards Disentangling Latent Space for Unsupervised Semantic Face Editing
• Vehicle Image Generation Going Well with The Surroundings
• What and Where to Translate: Local Mask-based Image-to-Image Translation
• An Adversarial Learning Based Approach for Unknown View Tomographic Reconstruction
• Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
• Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty
• Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision
• MixSyn: Learning Composition and Style for Multi-Source Image Synthesis
• ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network
• Bridging the Gap Between $f$-GANs and Wasserstein GANs
• When Relation Networks meet GANs: Relation GANs with Triplet Loss
• Trust the Critics: Generatorless and Multipurpose WGANs with Initial Convergence Guarantees
• Normalized Diversification
• Hole-robust Wireframe Detection
• The Geometric Occam's Razor Implicit in Deep Learning
• Face-to-Music Translation Using a Distance-Preserving Generative Adversarial Network with an Auxiliary Discriminator
• Synthetic-to-Real Domain Adaptation for Lane Detection
• GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation
• Neural Embedding for Physical Manipulations
• Disentanglement based Active Learning
• Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks
• Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks
• Information Compensation for Deep Conditional Generative Networks
• Imitation with Neural Density Models
• How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
• How Analysis Can Teach Us the Optimal Way to Design Neural Operators
• Effect of Various Regularizers on Model Complexities of Neural Networks in Presence of Input Noise
• Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
• On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration
• Noise Robust Generative Adversarial Networks
• Multimodal Image Outpainting With Regularized Normalized Diversification
• Test-Time Adaptation with Principal Component Analysis
• ARMA Nets: Expanding Receptive Field for Dense Prediction
• Incremental Scene Synthesis
• Class Balancing GAN with a Classifier in the Loop
• NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
• Generative Adversarial Learning via Kernel Density Discrimination
• A Survey on Adversarial Image Synthesis
• An Investigation into the Stochasticity of Batch Whitening
• NeuralDP Differentially private neural networks by design
• Dist-GAN: An Improved GAN using Distance Constraints
• Towards GANs' Approximation Ability
• A Contraction Approach to Model-based Reinforcement Learning
• MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
• Backpropagating through Fréchet Inception Distance
• Deep Automodulators
• FusedProp: Towards Efficient Training of Generative Adversarial Networks
• Inducing Optimal Attribute Representations for Conditional GANs
• Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
• Escaping from Collapsing Modes in a Constrained Space
• Generating Videos of Zero-Shot Compositions of Actions and Objects
• Learning with Hyperspherical Uniformity
• Nested Scale Editing for Conditional Image Synthesis
• Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory