VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part because they are prone to mode collapse, which means that they characterize only a few modes of the true distribution. To address this, we introduce VEEGAN, which features a reconstructor network, reversing the action of the generator by mapping from data to noise. Our training objective retains the original asymptotic consistency guarantee of GANs, and can be interpreted as a novel autoencoder loss over the noise. In sharp contrast to a traditional autoencoder over data points, VEEGAN does not require specifying a loss function over the data, but rather only over the representations, which are standard normal by assumption. On an extensive set of synthetic and real world image datasets, VEEGAN indeed resists mode collapsing to a far greater extent than other recent GAN variants, and produces more realistic samples.

• Publication year

  2017

• Venue

  Neural Information Processing Systems

• Publication date

  2017-05-22

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1705.07761
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GENERATIVE ADVERSARIAL NETS

  2018influential reference
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

  2017cited by this paper
• Deep and Hierarchical Implicit Models

  2017cited by this paper
• Adversarial Feature Learning

  2016influential reference
• Amortised MAP Inference for Image Super-resolution

  2016cited by this paper
• Unrolled Generative Adversarial Networks

  2016influential reference
• Adversarially Learned Inference

  2016influential reference
• Mode Regularized Generative Adversarial Networks

  2016influential reference
• Improved Techniques for Training GANs

  2016cited by this paper
• Autoencoding beyond pixels using a learned similarity metric

  2015cited by this paper
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

  2015influential reference
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models

  2014cited by this paper
• Deep Learning Face Attributes in the Wild

  2014cited by this paper
• Likelihood-free inference via classification

  2014cited by this paper
• Likelihood-free inference via classification

  2014cited by this paper
• Statistical Inference of Intractable Generative Models via Classification

  2014cited by this paper
• Auto-Encoding Variational Bayes

  2013cited by this paper
• Density Ratio Estimation in Machine Learning

  2012cited by this paper
• Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics

  2012cited by this paper
• Bregman divergence as general framework to estimate unnormalized statistical models

  2011cited by this paper
• Elements of Information Theory

  2005cited by this paper
• Monte Carlo Methods of Inference for Implicit Statistical Models

  1984cited by this paper

• Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation

  2026cites this paper
• Enhancing Stroke Prediction Using Generative Adversarial Networks for Intelligent Medical Care

  2026cites this paper
• Machine learning-based models for optical fiber channels

  2025cites this paper
• Task-free continual generative modelling via dynamic teacher-student framework

  2025cites this paper
• Diverse object placement with dual interaction

  2025cites this paper
• MAGIC: Noise Mitigation and Knowledge Alignment for Knowledge Graph-Based Multi-modal Recommendation

  2025cites this paper
• Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space

  2025cites this paper
• Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

  2025cites this paper
• Development of an injection molding production condition inference system based on diffusion model

  2025cites this paper
• esFont: A guided diffusion and multimodal distillation to enhance the efficiency and stability in font design

  2025cites this paper
• Quantum enhanced ensemble GANs for anomaly detection in continuous biomanufacturing

  2025cites this paper
• Structure-Preserving Medical Image Generation from a Latent Graph Representation

  2025cites this paper
• An effective design method of high-strength steel columns with limited datasets using physics-guided conditional tabular GAN

  2025cites this paper
• HarmonPaint: Harmonized Training-Free Diffusion Inpainting

  2025cites this paper
• PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing

  2025cites this paper
• Machine Learning in Acoustics: A Review and Open-source Repository

  2025cites this paper
• Release the Potential of Memory Buffer in Continual Learning: A Dynamic System Perspective

  2025cites this paper
• FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs

  2025cites this paper
• Data-driven 2D grain growth microstructure prediction using deep learning and spectral graph theory

  2025cites this paper
• Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints

  2025cites this paper
• HA-PointAE: A Novel Hybrid Attention PointNet Autoencoder for High-Fidelity Airfoil Generation and Aerodynamic Shape Optimization

  2025cites this paper
• Rehazing for Dehazing: A Physics-Guided Parametric Augmentation Net

  2025cites this paper
• Prediction of vehicle front wall sound insulation performance using Wasserstein generative adversarial network and Res-InceptionNet

  2025cites this paper
• Interactive Tumor Progression Modeling via Sketch-Based Image Editing

  2025cites this paper
• Generating Latent Space-Aware Test Cases for Neural Networks using Gradient-Based Search

  2025cites this paper
• Learning From Natural Images in Few-Shot SAR Target Classification

  2025cites this paper
• DiffCrysGen: A Score-Based Diffusion Model for Design of Diverse Inorganic Crystalline Materials

  2025cites this paper
• Synthetic Flight Data Generation Using Generative Models

  2025cites this paper
• DOOMGAN: High-Fidelity Dynamic Identity Obfuscation Ocular Generative Morphing

  2025cites this paper
• Hybrid machine learning framework for predicting pozzolanic reactivity: Integration of R3 test and GAN-augmented data

  2025cites this paper
• ESCFD: Probabilistic Flow Diffusion Model for Accelerated High-Quality Single-Cell RNA-seq Data Synthesis

  2025cites this paper
• Robust Missing Value Imputation With Proximal Optimal Transport for Low-Quality IIoT Data

  2025cites this paper
• Multivariate distribution fitting for GANs via introducing variable correlations

  2025cites this paper
• Preconditioned Regularized Wasserstein Proximal Sampling

  2025cites this paper
• Towards Mitigating Mode Collapse: An Entropy-Based Approach to Enhance WGAN

  2025cites this paper
• Generated Preserved Adversarial Federated Learning for Enhanced Image Analysis (GPAF)

  2025cites this paper
• Openness-aware multi-prototype learning for open set medical diagnosis

  2025cites this paper
• Unified Control for Inference-Time Guidance of Denoising Diffusion Models

  2025cites this paper
• Optimizing Dataset Quality and Diversity in Neural Networks: A Study of the Vendi Score

  2025cites this paper
• A Reliable Generative Adversarial Network Approach for Climate Downscaling and Weather Generation

  2025cites this paper
• MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation

  2025cites this paper
• Tumor Synthesis Conditioned on Radiomics

  2025cites this paper
• Feasibility study of unsupervised anomaly detection using Wasserstein GAN in SPECT image

  2025cites this paper
• Action-Inclusive Multi-Future Prediction Using a Generative Model in Human-Related Scenes for Mobile Robots

  2025cites this paper
• Advancing Marine Bioacoustics with Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection

  2025cites this paper
• Discrete Flow Matching is a Surprisingly Effective Post-training Method to Address Compound Error in Autoregressive Models

  2025cites this paper
• Training a Dynamic Growing Mixture Model for Lifelong Learning

  2025cites this paper
• Clinically informed semi-supervised learning improves disease annotation and equity from electronic health records: a glaucoma case study

  2025cites this paper
• Flexible Counterfactual Explanations with Generative Models

  2025cites this paper
• Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving

  2025cites this paper
• EBM-WGF: Training energy-based models with Wasserstein gradient flow

  2025cites this paper
• DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis

  2025cites this paper
• GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction

  2025cites this paper
• In the Blink of an Eye: Instant Game Map Editing using a Generative-AI Smart Brush

  2025cites this paper
• An in-depth review and analysis of mode collapse in generative adversarial networks

  2025cites this paper
• CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics

  2025influential citation
• Quantifying Generative Stability: Mode Collapse Entropy Score for Mode Diversity Evaluation

  2025influential citation
• On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models

  2025cites this paper
• Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review

  2025cites this paper
• Diversity in Stable GANs: A Systematic Review of Mode Collapse Mitigation Strategies

  2025cites this paper
• Deep learning based optical image super-resolution via generative diffusion models for layerwise in-situ LPBF monitoring

  2025cites this paper
• Optimal Transport with Arbitrary Prior for Dynamic Resolution Network

  2025cites this paper
• SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

  2024cites this paper
• Statistics Enhancement Generative Adversarial Networks for Diverse Conditional Image Synthesis

  2024cites this paper
• AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning

  2024cites this paper
• Permuted KPCA and SMOTE to Guide GAN-Based Oversampling for Imbalanced HSI Classification

  2024cites this paper
• FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian Perturbation

  2024cites this paper
• Copyright Protection in Generative AI: A Technical Perspective

  2024cites this paper
• Digital polycrystalline microstructure generation using diffusion probabilistic models

  2024cites this paper
• Navigation World Models

  2024cites this paper
• LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision

  2024cites this paper
• ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks

  2024cites this paper
• Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss

  2024cites this paper
• Using Diffusion Models as Generative Replay in Continual Federated Learning - What will Happen?

  2024cites this paper
• Denoising diffusion probabilistic models for generative alloy design

  2024cites this paper
• LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World

  2024cites this paper
• AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution

  2024cites this paper
• Artificial Intelligence for Biomedical Video Generation

  2024cites this paper
• Generative models for tabular data: A review

  2024influential citation
• Data generation scheme for photovoltaic power forecasting using Wasserstein GAN with gradient penalty combined with autoencoder and regression models

  2024cites this paper
• Evaluation Metrics and Methods for Generative Models in the Wireless PHY Layer

  2024cites this paper
• A novel spectral-spatial 3D auxiliary conditional GAN integrated convolutional LSTM for hyperspectral image classification

  2024cites this paper
• Investigating landslide data balancing for susceptibility mapping using generative and machine learning models

  2024cites this paper
• Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling

  2024cites this paper
• Manifold Constraint Regularization for Remote Sensing Image Generation

  2024cites this paper
• Denoising and Augmented Negative Sampling for Collaborative Filtering

  2024cites this paper
• AnyScene: Customized Image Synthesis with Composited Foreground

  2024cites this paper
• Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres

  2024cites this paper
• Diverse non-homogeneous texture synthesis from a single exemplar

  2024cites this paper
• Survey of Deep Learning and Physics-Based Approaches in Computational Wave Imaging

  2024cites this paper
• Generating Realistic Tabular Data with Large Language Models

  2024cites this paper
• Machine Learning Methods for Credit Card Fraud Detection: A Survey

  2024cites this paper
• NOTE: non-parametric oversampling technique for explainable credit scoring

  2024cites this paper
• DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room

  2024cites this paper
• Graph generative adversarial networks with evolutionary algorithm

  2024cites this paper
• CT-based synthetic contrast-enhanced dual-energy CT generation using conditional denoising diffusion probabilistic model

  2024cites this paper
• Kolmogorov-Smirnov GAN

  2024cites this paper
• A lightweight CNN model for pepper leaf disease recognition in a human palm background

  2024cites this paper
• Cross-dimensional knowledge-guided synthesizer trained with unpaired multimodality MRIs

  2024cites this paper
• DP-ImgSyn: Dataset Alignment for Obfuscated, Differentially Private Image Synthesis

  2024cites this paper