Improved Training of Wasserstein GANs

Abstract

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models over discrete data. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.

NIPS camera-ready

References in corpus (8)

• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• Boundary-Seeking Generative Adversarial Networks
• On distinguishability criteria for estimating generative models
• Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
• Recurrent Topic-Transition GAN for Visual Paragraph Generation
• Improved generator objectives for GANs

Cited by in corpus (460)

• Spectral Normalization for Generative Adversarial Networks
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Recent advances and clinical applications of deep learning in medical image analysis
• A Generative Model for Inverse Design of Metamaterials
• Training Generative Adversarial Networks with Limited Data
• Data Augmentation Generative Adversarial Networks
• The relativistic discriminator: a key element missing from standard GAN
• Deep Reinforcement Learning: An Overview
• MolGAN: An implicit generative model for small molecular graphs
• Generating Natural Adversarial Examples
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• cGANs with Projection Discriminator
• InfoVAE: Information Maximizing Variational Autoencoders
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• Differentially Private Generative Adversarial Network
• Generating 3D structures from a 2D slice with GAN-based dimensionality expansion
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• 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
• Image Inpainting via Generative Multi-column Convolutional Neural Networks
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Generating Adversarial Examples with Adversarial Networks
• An empirical study on evaluation metrics of generative adversarial networks
• Learning to Predict the Cosmological Structure Formation
• Generative Image Inpainting with Contextual Attention
• Synthesizing Tabular Data using Generative Adversarial Networks
• Stabilizing Training of Generative Adversarial Networks through Regularization
• A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
• Continual Learning with Deep Generative Replay
• NetGAN: Generating Graphs via Random Walks
• Wasserstein Auto-Encoders
• The Numerics of GANs
• How to GAN LHC Events
• Masking: A New Perspective of Noisy Supervision
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• On the regularization of Wasserstein GANs
• A survey on text generation using generative adversarial networks
• Generative Adversarial Active Learning
• SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
• Video-to-Video Synthesis
• Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
• Visual enhancement of Cone-beam CT by use of CycleGAN
• Boundary-Seeking Generative Adversarial Networks
• From Variational to Deterministic Autoencoders
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• AI-assisted super-resolution cosmological simulations
• Adversarial Generation of Natural Language
• Generative Models for Automatic Chemical Design
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Language Generation with Recurrent Generative Adversarial Networks without Pre-training
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
• Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
• ChatPainter: Improving Text to Image Generation using Dialogue
• On Accurate Evaluation of GANs for Language Generation
• A-NICE-MC: Adversarial Training for MCMC
• Learning Generative Models with Sinkhorn Divergences
• Super-resolution emulator of cosmological simulations using deep physical models
• Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
• On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
• Stabilizing Generative Adversarial Networks: A Survey
• Improved Adversarial Systems for 3D Object Generation and Reconstruction
• Geometry Score: A Method For Comparing Generative Adversarial Networks
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching
• Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions
• Wasserstein Learning of Deep Generative Point Process Models
• Detecting outliers in astronomical images with deep generative networks
• Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
• TBD: Benchmarking and Analyzing Deep Neural Network Training
• MAGAN: Margin Adaptation for Generative Adversarial Networks
• Pseudo-healthy synthesis with pathology disentanglement and adversarial learning
• Exposure: A White-Box Photo Post-Processing Framework
• On gradient regularizers for MMD GANs
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Geometry-Contrastive GAN for Facial Expression Transfer
• Learning Independent Features with Adversarial Nets for Non-linear ICA
• Is Generator Conditioning Causally Related to GAN Performance?
• Activation Maximization Generative Adversarial Nets
• Convergence Problems with Generative Adversarial Networks (GANs)
• Generating Multi-Categorical Samples with Generative Adversarial Networks
• TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution
• Conditional Sig-Wasserstein GANs for Time Series Generation
• Generative Models for Low-Rank Video Representation and Reconstruction
• Comparison of Maximum Likelihood and GAN-based training of Real NVPs
• CR-GAN: Learning Complete Representations for Multi-view Generation
• Void Filling of Digital Elevation Models with Deep Generative Models
• Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures
• AGAN: Towards Automated Design of Generative Adversarial Networks
• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
• Adversarially Regularized Autoencoders
• A Convex Duality Framework for GANs
• SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
• 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
• Anomaly detection and automatic labeling for solar cell quality inspection based on Generative Adversarial Network
• Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• Understanding GANs: the LQG Setting
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks
• Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
• Decentralized and Robust Privacy-Preserving Model Using Blockchain-Enabled Federated Deep Learning in Intelligent Enterprises
• Design by adaptive sampling
• Stabilizing Invertible Neural Networks Using Mixture Models
• Airline Passenger Name Record Generation using Generative Adversarial Networks
• Class-Splitting Generative Adversarial Networks
• Text to Image Synthesis Using Generative Adversarial Networks
• Stochastic Restoration of Heavily Compressed Musical Audio using Generative Adversarial Networks
• CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer
• Adversarial Distillation of Bayesian Neural Network Posteriors
• Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
• AutoLoss: Learning Discrete Schedules for Alternate Optimization
• Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data
• On the Benefit of Adversarial Training for Monocular Depth Estimation
• Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers
• Improved Training of Generative Adversarial Networks Using Representative Features
• 3D Object Reconstruction from a Single Depth View with Adversarial Learning
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• Perceptual Image Anomaly Detection
• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• Low-Resource Text Classification using Domain-Adversarial Learning
• DeepFlow: History Matching in the Space of Deep Generative Models
• GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
• Structured Generative Adversarial Networks
• Image to Image Translation for Domain Adaptation
• Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
• Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties
• A Divergence Minimization Perspective on Imitation Learning Methods
• Unsupervised Cipher Cracking Using Discrete GANs
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• Neural Language Generation: Formulation, Methods, and Evaluation
• Mode Collapse and Regularity of Optimal Transportation Maps
• Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
• Adversarial Text Generation Without Reinforcement Learning
• 2-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANs
• Stability-certified reinforcement learning: A control-theoretic perspective
• Self-Supervised Variational Auto-Encoders
• Decompose to manipulate: Manipulable Object Synthesis in 3D Medical Images with Structured Image Decomposition
• Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• Attacking Speaker Recognition With Deep Generative Models
• Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
• Latent Convolutional Models
• Disentangled Makeup Transfer with Generative Adversarial Network
• eCommerceGAN : A Generative Adversarial Network for E-commerce
• Exploring the Evolution of GANs through Quality Diversity
• Adversarial Variational Optimization of Non-Differentiable Simulators
• Towards a Better Understanding and Regularization of GAN Training Dynamics
• Adversarial Contrastive Estimation
• GANGs: Generative Adversarial Network Games
• Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset
• A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
• What Matters for Adversarial Imitation Learning?
• MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
• Metropolis-Hastings Generative Adversarial Networks
• Robust learning with implicit residual networks
• Compressing PDF sets using generative adversarial networks
• Learned convex regularizers for inverse problems
• An error analysis of generative adversarial networks for learning distributions
• Finding Mixed Nash Equilibria of Generative Adversarial Networks
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• On the Effectiveness of Least Squares Generative Adversarial Networks
• SALSA-TEXT : self attentive latent space based adversarial text generation
• Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• DOOM Level Generation using Generative Adversarial Networks
• Deep Generative Models for Distribution-Preserving Lossy Compression
• Packet-Level Adversarial Network Traffic Crafting using Sequence Generative Adversarial Networks
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• Local and non-local dependency learning and emergence of rule-like representations in speech data by Deep Convolutional Generative Adversarial Networks
• CMB-GAN: Fast Simulations of Cosmic Microwave background anisotropy maps using Deep Learning
• Triple consistency loss for pairing distributions in GAN-based face synthesis
• Dual Swap Disentangling
• Accelerating Bayesian microseismic event location with deep learning
• Common Spatial Generative Adversarial Networks based EEG Data Augmentation for Cross-Subject Brain-Computer Interface
• Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks
• RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks
• Deep Learning of Dynamic Subsurface Flow via Theory-guided Generative Adversarial Network
• Quantitatively Evaluating GANs With Divergences Proposed for Training
• LOGAN: Membership Inference Attacks Against Generative Models
• Improving the quality of generative models through Smirnov transformation
• Learning Shape Priors for Single-View 3D Completion and Reconstruction
• Blood Vessel Geometry Synthesis using Generative Adversarial Networks
• TequilaGAN: How to easily identify GAN samples
• Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
• Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
• Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Poverty
• Disentangling Multiple Conditional Inputs in GANs
• New Era of Deeplearning-Based Malware Intrusion Detection: The Malware Detection and Prediction Based On Deep Learning
• RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
• Modular Generative Adversarial Networks
• Bounded Information Rate Variational Autoencoders
• Composite Functional Gradient Learning of Generative Adversarial Models
• Densely connected normalizing flows
• GAN-powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicing
• Primal-Dual Wasserstein GAN
• Fluid Flow Mass Transport for Generative Networks
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
• Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
• Using generative adversarial networks to synthesize artificial financial datasets
• Optimal transport maps for distribution preserving operations on latent spaces of Generative Models
• Improved Training with Curriculum GANs
• Adversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems
• Comparing Generative Adversarial Network Techniques for Image Creation and Modification
• Training Generative Adversarial Networks Via Turing Test
• Subgrid-scale parametrization of unresolved scales in forced Burgers equation using Generative Adversarial Networks (GAN)
• Learning Deep Hidden Nonlinear Dynamics from Aggregate Data
• Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments
• Reconstruction of Protein Structures from Single-Molecule Time Series
• 3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations
• Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations
• Improving LIME Robustness with Smarter Locality Sampling
• Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
• Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
• The Devil is in the Decoder: Classification, Regression and GANs
• Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
• Face Translation between Images and Videos using Identity-aware CycleGAN
• QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with Increased Receptive Field
• ACtuAL: Actor-Critic Under Adversarial Learning
• Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
• Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
• Generating Synthetic Multispectral Satellite Imagery from Sentinel-2
• Generative Adversarial Networks for Crystal Structure Prediction
• Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
• Compressed Sensing: From Research to Clinical Practice with Data-Driven Learning
• Few-shot Video-to-Video Synthesis
• RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series
• Wasserstein Variational Inference
• Deriving Machine Attention from Human Rationales
• General-to-Detailed GAN for Infrequent Class Medical Images
• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Recent Advances of Image Steganography with Generative Adversarial Networks
• Learning the Precise Feature for Cluster Assignment
• KG-GAN: Knowledge-Guided Generative Adversarial Networks
• Self-Supervised GANs with Label Augmentation
• Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
• DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution
• Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization
• Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networks
• GAN-based Generation and Automatic Selection of Explanations for Neural Networks
• GANs beyond divergence minimization
• Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
• Anomaly detection with Wasserstein GAN
• Inverse Estimation of Elastic Modulus Using Physics-Informed Generative Adversarial Networks
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Metric Learning-based Generative Adversarial Network
• Performing Co-Membership Attacks Against Deep Generative Models
• Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models
• Statistical analysis of Wasserstein GANs with applications to time series forecasting
• Image-derived generative modeling of pseudo-macromolecular structures - towards the statistical assessment of Electron CryoTomography template matching
• Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks
• Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification
• PAGAN: Portfolio Analysis with Generative Adversarial Networks
• Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN
• Gaussian-Smooth Optimal Transport: Metric Structure and Statistical Efficiency
• Towards Better Long-range Time Series Forecasting using Generative Adversarial Networks
• Unsupervised 3D Shape Learning from Image Collections in the Wild
• Generation of Synthetic Electronic Health Records Using a Federated GAN
• Unsupervised Change Detection in Satellite Images with Generative Adversarial Network
• toon2real: Translating Cartoon Images to Realistic Images
• Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization
• AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
• WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks
• SeismoGen: Seismic Waveform Synthesis Using Generative Adversarial Networks
• Learning to Synthesize Fashion Textures
• Controllable Descendant Face Synthesis
• Variance Regularizing Adversarial Learning
• BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN
• A Wasserstein GAN model with the total variational regularization
• Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• Generalized Energy Based Models
• FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network
• Generation High resolution 3D model from natural language by Generative Adversarial Network
• Adversarial Regression. Generative Adversarial Networks for Non-Linear Regression: Theory and Assessment
• Deep 3D-Zoom Net: Unsupervised Learning of Photo-Realistic 3D-Zoom
• Tree-Wasserstein Barycenter for Large-Scale Multilevel Clustering and Scalable Bayes
• Score-Guided Generative Adversarial Networks
• EnvGAN: Adversarial Synthesis of Environmental Sounds for Data Augmentation
• Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis
• Improving Federated Relational Data Modeling via Basis Alignment and Weight Penalty
• Measuring Fairness in Generative Models
• Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
• Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network
• PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening
• No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks
• Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
• Extractive Summary as Discrete Latent Variables
• Hyperprior Induced Unsupervised Disentanglement of Latent Representations
• Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification
• Generative Adversarial Forests for Better Conditioned Adversarial Learning
• Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
• Adversarial Constraint Learning for Structured Prediction
• BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification
• Generative Adversarial Mapping Networks
• Modeling EEG data distribution with a Wasserstein Generative Adversarial Network to predict RSVP Events
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging
• Matrix Normal PCA for Interpretable Dimension Reduction and Graphical Noise Modeling
• Bayesian Reasoning with Trained Neural Networks
• Manifold Interpolation for Large-Scale Multi-Objective Optimization via Generative Adversarial Networks
• Image-based Plant Disease Diagnosis with Unsupervised Anomaly Detection Based on Reconstructability of Colors
• CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
• SDE approximations of GANs training and its long-run behavior
• Learning Disentangled Representations of Satellite Image Time Series
• Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
• Extreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization
• Variational Diffusion Autoencoders with Random Walk Sampling
• Boosting Image Outpainting with Semantic Layout Prediction
• Product-Aware Answer Generation in E-Commerce Question-Answering
• Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
• Correcting Nuisance Variation using Wasserstein Distance
• Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• Deep Convolutional GANs for Car Image Generation
• Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models
• Kernel-Based Training of Generative Networks
• Parametric Synthesis of Text on Stylized Backgrounds using PGGANs
• Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
• Generative-Discriminative Complementary Learning
• On Lipschitz Bounds of General Convolutional Neural Networks
• Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network
• Curriculum Learning for Deep Generative Models with Clustering
• Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior
• Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
• FIS-GAN: GAN with Flow-based Importance Sampling
• Adversarially Learned Mixture Model
• Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs
• A Novel Framework for Selection of GANs for an Application
• Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency
• Self-Sampling for Neural Point Cloud Consolidation
• Batch Normalization in the final layer of generative networks
• Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation
• The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
• Double Descent and Other Interpolation Phenomena in GANs
• SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching
• EVGen: Adversarial Networks for Learning Electric Vehicle Charging Loads and Hidden Representations
• Generative Visual Rationales
• Manifold-preserved GANs
• MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks
• On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow
• Few-shot Continual Learning: a Brain-inspired Approach
• Discriminative Active Learning for Domain Adaptation
• Weakly Supervised Audio Source Separation via Spectrum Energy Preserved Wasserstein Learning
• Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition
• TET-GAN: Text Effects Transfer via Stylization and Destylization
• Sliced Wasserstein Generative Models
• Adversarial Binary Coding for Efficient Person Re-identification
• Speech Enhancement-assisted Voice Conversion in Noisy Environments
• OCT-GAN: Neural ODE-based Conditional Tabular GANs
• f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
• Fast Computational Ghost Imaging using Unpaired Deep Learning and a Constrained Generative Adversarial Network
• An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation
• TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing
• Defo-Net: Learning Body Deformation using Generative Adversarial Networks
• A Survey on GAN Acceleration Using Memory Compression Technique
• Does Adversarial Oversampling Help us?
• Language Modeling with Generative Adversarial Networks
• LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
• Generative Spatiotemporal Modeling Of Neutrophil Behavior
• Updating the generator in PPGN-h with gradients flowing through the encoder
• Text-to-image Synthesis via Symmetrical Distillation Networks
• Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text
• Capturing the diversity of biological tuning curves using generative adversarial networks
• Data-driven Accelerogram Synthesis using Deep Generative Models
• Robust Attacks on Deep Learning Face Recognition in the Physical World
• GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
• Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets
• A Statistician Teaches Deep Learning
• End-to-end Generative Zero-shot Learning via Few-shot Learning
• OntoZSL: Ontology-enhanced Zero-shot Learning
• CIZSL++: Creativity Inspired Generative Zero-Shot Learning
• Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks
• SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms
• Wasserstein GAN Can Perform PCA
• Generating Realistic Sequences of Customer-level Transactions for Retail Datasets
• Synthetic Dynamic PMU Data Generation: A Generative Adversarial Network Approach
• Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
• Wasserstein Introspective Neural Networks
• An Iterative Closest Points Approach to Neural Generative Models
• Implicit Manifold Learning on Generative Adversarial Networks
• Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification
• Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning
• LoGAN: Generating Logos with a Generative Adversarial Neural Network Conditioned on color
• Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
• Guiding the One-to-one Mapping in CycleGAN via Optimal Transport
• Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning
• Out-of-Sample Testing for GANs
• Posterior asymptotics in Wasserstein metrics on the real line
• Deep PDF: Probabilistic Surface Optimization and Density Estimation
• Adaptive Wasserstein Hourglass for Weakly Supervised Hand Pose Estimation from Monocular RGB
• SparseGAN: Sparse Generative Adversarial Network for Text Generation
• Semi-Supervised Learning with IPM-based GANs: an Empirical Study
• On reproduction of On the regularization of Wasserstein GANs
• Visual Analogies between Atari Games for Studying Transfer Learning in RL
• Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder
• LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders
• Resampling Base Distributions of Normalizing Flows
• CanvasGAN: A simple baseline for text to image generation by incrementally patching a canvas
• Coupling Matrix Manifolds and Their Applications in Optimal Transport
• Ambient Hidden Space of Generative Adversarial Networks
• Image Translation for Medical Image Generation -- Ischemic Stroke Lesions
• Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation
• Diversity Regularized Adversarial Learning
• Zero-Shot Learning Based on Knowledge Sharing
• Molecular Attributes Transfer from Non-Parallel Data
• Synthesizing Photorealistic Images with Deep Generative Learning
• Moreau-Yosida $f$-divergences
• Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
• A Frequency Domain Constraint for Synthetic and Real X-ray Image Super Resolution
• What and Where to Translate: Local Mask-based Image-to-Image Translation
• NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
• ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data
• Lesion-Inspired Denoising Network: Connecting Medical Image Denoising and Lesion Detection
• Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting
• Disassembling Object Representations without Labels
• Point Cloud Colorization Based on Densely Annotated 3D Shape Dataset
• NeuralDP Differentially private neural networks by design
• Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification
• Towards Language Agnostic Universal Representations
• Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data
• Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• Quality-aware Unpaired Image-to-Image Translation
• Attending Category Disentangled Global Context for Image Classification
• High Diversity Attribute Guided Face Generation with GANs
• Local Stability and Performance of Simple Gradient Penalty mu-Wasserstein GAN
• LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network
• An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution
• Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
• Video-to-Video Translation for Visual Speech Synthesis
• LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation
• Deep Direct Likelihood Knockoffs
• Single Frame Deblurring with Laplacian Filters
• Learning convex regularizers satisfying the variational source condition for inverse problems
• EarthGAN: Can we visualize the Earth's mantle convection using a surrogate model?
• Iterative Update and Unified Representation for Multi-Agent Reinforcement Learning
• Generating the support with extreme value losses
• Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks
• Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case
• SimuGAN: Unsupervised forward modeling and optimal design of a LIDAR Camera
• Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery
• Motion Generation Considering Situation with Conditional Generative Adversarial Networks for Throwing Robots
• Can adversarial training learn image captioning ?