Wasserstein GAN

Abstract

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.

Cited by in corpus (100)

• Deep Visual Domain Adaptation: A Survey
• Generative Adversarial Network in Medical Imaging: A Review
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Graph Neural Network for Traffic Forecasting: A Survey
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• Deep Generative Design: Integration of Topology Optimization and Generative Models
• Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis
• On the Reconstruction of Face Images from Deep Face Templates
• Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Cross-Subject Transfer Learning in Human Activity Recognition Systems using Generative Adversarial Networks
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting
• A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• The Metric Space of Collider Events
• Structure-Preserving Image Super-Resolution
• AtlFast3: the next generation of fast simulation in ATLAS
• Deep Knockoffs
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Regressive and generative neural networks for scalar field theory
• AI-assisted super-resolution cosmological simulations
• Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology
• Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
• Convergence and Concentration of Empirical Measures under Wasserstein Distance in Unbounded Functional Spaces
• PPGAN: Privacy-preserving Generative Adversarial Network
• Learning quantum data with the quantum Earth Mover's distance
• Super-resolution emulator of cosmological simulations using deep physical models
• Domain Generalization via Optimal Transport with Metric Similarity Learning
• Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeters
• Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles
• Unnormalized Optimal Transport
• Dual Adversarial Auto-Encoders for Clustering
• Detecting outliers in astronomical images with deep generative networks
• Cycle-Consistent Speech Enhancement
• Spatial Evolutionary Generative Adversarial Networks
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• Visual-Tactile Cross-Modal Data Generation using Residue-Fusion GAN with Feature-Matching and Perceptual Losses
• Adversarial-Residual-Coarse-Graining: Applying machine learning theory to systematic molecular coarse-graining
• GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning
• A topological encoding method for data-driven photonics inverse design
• Digital rock reconstruction with user-defined properties using conditional generative adversarial networks
• The quadratic Wasserstein metric for earthquake location
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery
• Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
• ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
• Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
• Feature-aware conditional GAN for category text generation
• Dim but not entirely dark: Extracting the Galactic Center Excess' source-count distribution with neural nets
• JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
• ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis
• Simple yet Effective Way for Improving the Performance of GAN
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks
• Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks
• Low-Resource Text Classification using Domain-Adversarial Learning
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud
• Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition
• Brain MRI Tumor Segmentation with Adversarial Networks
• GRASS: Generative Recursive Autoencoders for Shape Structures
• TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
• Generalized Unnormalized Optimal Transport and its fast algorithms
• Justifying Diagnosis Decisions by Deep Neural Networks
• Differentially Private Generative Adversarial Networks with Model Inversion
• Deblending Galaxies with Generative Adversarial Networks
• Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation
• Procedural content generation of puzzle games using conditional generative adversarial networks
• Accelerating Bayesian microseismic event location with deep learning
• AI-assisted super-resolution cosmological simulations III: Time evolution
• Anisotropic Stroke Control for Multiple Artists Style Transfer
• Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN
• Understanding Compressive Adversarial Privacy
• Near-Term Quantum-Classical Associative Adversarial Networks
• Generative Convolution Layer for Image Generation
• Categorical EHR Imputation with Generative Adversarial Nets
• Image Processing Using Multi-Code GAN Prior
• Deep learning reconstruction of three-dimensional galaxy distributions with intensity mapping observations
• Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
• Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
• Dynamics of Fourier Modes in Torus Generative Adversarial Networks
• An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Solving general elliptical mixture models through an approximate Wasserstein manifold
• Meta Learning for Few-Shot One-class Classification
• Are You A Risk Taker? Adversarial Learning of Asymmetric Cross-Domain Alignment for Risk Tolerance Prediction
• A Mathematical Framework for Learning Probability Distributions
• Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
• AIBench Scenario: Scenario-distilling AI Benchmarking
• Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe
• Multiqubit state learning with entangling quantum generative adversarial networks
• MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
• Synthetic Data Generation for Classifying Electrophysiological and Morpho-Electrophysiological Neurons from Mouse Visual Cortex
• Adaptive Divergence for Rapid Adversarial Optimization
• Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization
• Scalable Personalised Item Ranking through Parametric Density Estimation
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations