{"url":"/method/wgan-gp","slug":"wgan-gp","name":"WGAN GP","full_name":"Wasserstein GAN (Gradient Penalty)","full_name_withheld":false,"description_markdown":"**Wasserstein GAN + Gradient Penalty**, or **WGAN-GP**, is a generative adversarial network that uses the Wasserstein loss formulation plus a gradient norm penalty to achieve Lipschitz continuity.\r\n\r\nThe original [WGAN](https://paperswithcode.com/method/wgan) uses weight clipping to achieve 1-Lipschitz functions, but this can lead to undesirable behaviour by creating pathological value surfaces and capacity underuse, as well as gradient explosion/vanishing without careful tuning of the weight clipping parameter $c$.\r\n\r\nA Gradient Penalty is a soft version of the Lipschitz constraint, which follows from the fact that functions are 1-Lipschitz iff the gradients are of norm at most 1 everywhere. The squared difference from norm 1 is used as the gradient penalty.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Improved Training of Wasserstein GANs","paper":"/paper/improved-training-of-wasserstein-gans","first_author":"Ishaan Gulrajani","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/improved-training-of-wasserstein-gans"},"source":{"url":"http://arxiv.org/abs/1704.00028v3","title":"Improved Training of Wasserstein GANs","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/wgan_gp/wgan_gp.py","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":11,"archive_num_papers":11,"papers_newest_first":[{"paper":"/paper/fairgan-gans-based-fairness-aware-learning","title":"FairGAN: GANs-based Fairness-aware Learning for Recommendations with Implicit Feedback","date":"2022-04-25","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":"/paper/priorgan-real-data-prior-for-generative","title":"PriorGAN: Real Data Prior for Generative Adversarial Nets","date":"2020-06-30","arxiv_id":"2006.16990","n_code_links":1,"syntology":null},{"paper":"/paper/mimicry-towards-the-reproducibility-of-gan-1","title":"Mimicry: Towards the Reproducibility of GAN Research","date":"2020-05-05","arxiv_id":"2005.02494","n_code_links":3,"syntology":null},{"paper":null,"title":"Generating Geological Facies Models with Fidelity to Diversity and Statistics of Training Images using Improved Generative Adversarial Networks","date":"2019-09-23","arxiv_id":"1909.10652","n_code_links":0,"syntology":null},{"paper":"/paper/how-can-we-make-gan-perform-better-in-single","title":"How Can We Make GAN Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approach","date":"2019-01-10","arxiv_id":"1901.03419","n_code_links":2,"syntology":null},{"paper":"/paper/convolutional-generative-adversarial-networks","title":"Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation","date":"2018-04-25","arxiv_id":"1804.09399","n_code_links":3,"syntology":{"ran":0,"of":35,"unverified":35,"pointer_only":0}},{"paper":null,"title":"Language Modeling with Generative AdversarialNetworks","date":"2018-04-08","arxiv_id":"1804.02617","n_code_links":0,"syntology":null},{"paper":"/paper/gans-trained-by-a-two-time-scale-update-rule","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","date":"2017-06-26","arxiv_id":"1706.08500","n_code_links":71,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":1}},{"paper":"/paper/continual-learning-with-deep-generative","title":"Continual Learning with Deep Generative Replay","date":"2017-05-24","arxiv_id":"1705.08690","n_code_links":5,"syntology":null},{"paper":"/paper/improved-training-of-wasserstein-gans","title":"Improved Training of Wasserstein GANs","date":"2017-03-31","arxiv_id":"1704.00028","n_code_links":110,"syntology":{"ran":27,"of":49,"unverified":22,"pointer_only":20}}],"papers_shown":11,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":3},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":null,"name":"Generative Adversarial Network","papers":2},{"task":"/task/class-incremental-learning","name":"Class Incremental Learning","papers":1},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":1},{"task":"/task/continual-learning","name":"Continual Learning","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/disentanglement","name":"Disentanglement","papers":1},{"task":"/task/emotion-recognition-in-conversation","name":"Emotion Recognition in Conversation","papers":1},{"task":"/task/exposure-fairness","name":"Exposure Fairness","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":null,"name":"Hippocampus","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/music-generation","name":"Music Generation","papers":1},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":1}],"tasks_shown":20,"n_tasks":26,"usage_by_year":[{"year":"2017","papers":3},{"year":"2018","papers":2},{"year":"2019","papers":2},{"year":"2020","papers":2},{"year":"2021","papers":1},{"year":"2022","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-gp"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}