{"url":"/method/wgan","slug":"wgan","name":"WGAN","full_name":"Wasserstein GAN","full_name_withheld":false,"description_markdown":"**Wasserstein GAN**, or **WGAN**, is a type of generative adversarial network that minimizes an approximation of the Earth-Mover's distance (EM) rather than the Jensen-Shannon divergence as in the original [GAN](https://paperswithcode.com/method/gan) formulation. It leads to more stable training than original GANs with less evidence of mode collapse, as well as meaningful curves that can be used for debugging and searching hyperparameters.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Wasserstein GAN","paper":"/paper/wasserstein-gan","first_author":"Martin Arjovsky","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/wasserstein-gan"},"source":{"url":"http://arxiv.org/abs/1701.07875v3","title":"Wasserstein GAN","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/daheyinyin/wgan","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Adversarial Networks","url":"/methods/category/generative-adversarial-networks","pwc_aliases":[]}],"n_papers_tagged":95,"archive_num_papers":95,"papers_newest_first":[{"paper":null,"title":"Time-series surrogates from energy consumers generated by machine learning approaches for long-term forecasting scenarios","date":"2025-06-25","arxiv_id":"2506.20253","n_code_links":0,"syntology":null},{"paper":null,"title":"Risk Management with Feature-Enriched Generative Adversarial Networks (FE-GAN)","date":"2024-11-23","arxiv_id":"2411.15519","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhanced Anime Image Generation Using USE-CMHSA-GAN","date":"2024-11-17","arxiv_id":"2411.11179","n_code_links":0,"syntology":null},{"paper":null,"title":"Statistical Error Bounds for GANs with Nonlinear Objective Functionals","date":"2024-06-24","arxiv_id":"2406.16834","n_code_links":0,"syntology":null},{"paper":null,"title":"A Differential Equation Approach for Wasserstein GANs and Beyond","date":"2024-05-25","arxiv_id":"2405.16351","n_code_links":0,"syntology":null},{"paper":"/paper/s3r-net-a-single-stage-approach-to-self","title":"S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal","date":"2024-04-18","arxiv_id":"2404.12103","n_code_links":1,"syntology":null},{"paper":null,"title":"A CT Image Denoising Method with Residual Encoder-Decoder Network","date":"2024-04-02","arxiv_id":"2404.01553","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Generative Modeling via Penalized Optimal Transport Network","date":"2024-02-16","arxiv_id":"2402.10456","n_code_links":0,"syntology":null},{"paper":"/paper/improving-eeg-signal-classification-accuracy","title":"Improving EEG Signal Classification Accuracy Using Wasserstein Generative Adversarial Networks","date":"2024-02-05","arxiv_id":"2402.09453","n_code_links":1,"syntology":null},{"paper":"/paper/adversarial-score-distillation-when-score","title":"Adversarial Score Distillation: When score distillation meets GAN","date":"2023-12-01","arxiv_id":"2312.00739","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":"/paper/stroke-based-neural-painting-and-stylization","title":"Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region","date":"2023-09-07","arxiv_id":"2309.03504","n_code_links":2,"syntology":null},{"paper":"/paper/comgan-toward-gans-exploiting-multiple","title":"ComGAN: Toward GANs Exploiting Multiple Samples","date":"2023-04-24","arxiv_id":"2304.12098","n_code_links":1,"syntology":null},{"paper":"/paper/energy-guided-entropic-neural-optimal","title":"Energy-guided Entropic Neural Optimal Transport","date":"2023-04-12","arxiv_id":"2304.06094","n_code_links":1,"syntology":{"ran":0,"of":11,"unverified":11,"pointer_only":0}},{"paper":"/paper/diffusion-probabilistic-models-beat-gans-on","title":"Diffusion Probabilistic Models beat GANs on Medical Images","date":"2022-12-14","arxiv_id":"2212.07501","n_code_links":1,"syntology":null},{"paper":"/paper/resolving-semantic-confusions-for-improved-1","title":"Resolving Semantic Confusions for Improved Zero-Shot Detection","date":"2022-12-12","arxiv_id":"2212.06097","n_code_links":1,"syntology":null},{"paper":null,"title":"DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics","date":"2022-09-26","arxiv_id":"2209.13592","n_code_links":0,"syntology":null},{"paper":null,"title":"Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN","date":"2022-09-21","arxiv_id":"2209.10446","n_code_links":0,"syntology":null},{"paper":"/paper/kantorovich-strikes-back-wasserstein-gans-are","title":"Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?","date":"2022-06-15","arxiv_id":"2206.07767","n_code_links":2,"syntology":{"ran":0,"of":12,"unverified":12,"pointer_only":0}},{"paper":null,"title":"Demand Response Method Considering Multiple Types of Flexible Loads in Industrial Parks","date":"2022-05-24","arxiv_id":"2205.11743","n_code_links":0,"syntology":null},{"paper":null,"title":"Alternative Data Augmentation for Industrial Monitoring using Adversarial Learning","date":"2022-05-09","arxiv_id":"2205.04222","n_code_links":0,"syntology":null},{"paper":null,"title":"Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning","date":"2022-03-28","arxiv_id":"2203.14794","n_code_links":0,"syntology":null},{"paper":"/paper/neural-network-training-under-semidefinite","title":"Neural network training under semidefinite constraints","date":"2022-01-03","arxiv_id":"2201.00632","n_code_links":1,"syntology":null},{"paper":"/paper/gm-score-incorporating-inter-class-and-intra","title":"GM Score: Incorporating inter-class and intra-class generator diversity, discriminability of disentangled representation, and sample fidelity for evaluating GANs","date":"2021-12-13","arxiv_id":"2112.06431","n_code_links":1,"syntology":null},{"paper":"/paper/synthetic-ecg-signal-generation-using","title":"Synthetic ECG Signal Generation Using Generative Neural Networks","date":"2021-12-05","arxiv_id":"2112.03268","n_code_links":1,"syntology":null},{"paper":"/paper/trust-the-critics-generatorless-and","title":"Trust the Critics: Generatorless and Multipurpose WGANs with Initial Convergence Guarantees","date":"2021-11-30","arxiv_id":"2111.15099","n_code_links":1,"syntology":null},{"paper":"/paper/physics-driven-learning-of-wasserstein-gan","title":"Physics-Driven Learning of Wasserstein GAN for Density Reconstruction in Dynamic Tomography","date":"2021-10-28","arxiv_id":"2110.15424","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-generative-neural-network","title":"Investigating generative neural-network models for building pest insect detectors in sticky trap images for the Peruvian horticulture","date":"2021-10-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Alleviating Mode Collapse in GAN via Diversity Penalty Module","date":"2021-08-05","arxiv_id":"2108.02353","n_code_links":0,"syntology":null},{"paper":null,"title":"Synthetic Periocular Iris PAI from a Small Set of Near-Infrared-Images","date":"2021-07-26","arxiv_id":"2107.12014","n_code_links":0,"syntology":null},{"paper":null,"title":"Generalization Error of GAN from the Discriminator's Perspective","date":"2021-07-08","arxiv_id":"2107.03633","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":null,"name":"Generative Adversarial Network","papers":24},{"task":"/task/image-generation","name":"Image Generation","papers":15},{"task":"/task/denoising","name":"Denoising","papers":7},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4},{"task":"/task/diversity","name":"Diversity","papers":4},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":4},{"task":"/task/time-series-1","name":"Time Series","papers":4},{"task":"/task/time-series","name":"Time Series Analysis","papers":4},{"task":"/task/synthetic-data-generation","name":"Synthetic Data Generation","papers":3},{"task":"/task/translation","name":"Translation","papers":3},{"task":null,"name":"CPU","papers":2},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/eeg-1","name":"EEG","papers":2},{"task":"/task/classification","name":"General Classification","papers":2},{"task":"/task/image-denoising","name":"Image Denoising","papers":2},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":2},{"task":"/task/management","name":"Management","papers":2},{"task":"/task/ssim","name":"SSIM","papers":2},{"task":"/task/super-resolution","name":"Super-Resolution","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2}],"tasks_shown":20,"n_tasks":85,"usage_by_year":[{"year":"2017","papers":8},{"year":"2018","papers":16},{"year":"2019","papers":18},{"year":"2020","papers":13},{"year":"2021","papers":18},{"year":"2022","papers":9},{"year":"2023","papers":4},{"year":"2024","papers":8},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/wgan"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}