{"url":"/method/bigan","slug":"bigan","name":"BiGAN","full_name":"Bidirectional GAN","full_name_withheld":false,"description_markdown":"A **BiGAN**, or **Bidirectional GAN**, is a type of generative adversarial network where the generator  not only maps latent samples to generated data, but also has an inverse mapping from data to the latent representation. The motivation is to make a type of GAN that can learn rich representations for us in applications like unsupervised learning.\r\n\r\nIn addition to the generator $G$ from the standard [GAN](https://paperswithcode.com/method/gan) framework, BiGAN includes an encoder $E$ which maps data $\\mathbf{x}$ to latent representations $\\mathbf{z}$. The BiGAN discriminator $D$ discriminates not only in data space ($\\mathbf{x}$ versus $G\\left(\\mathbf{z}\\right)$), but jointly in data and latent space (tuples $\\left(\\mathbf{x}, E\\left(\\mathbf{x}\\right)\\right)$ versus $\\left(G\\left(z\\right), z\\right)$), where the latent component is either an encoder output $E\\left(\\mathbf{x}\\right)$ or a generator input $\\mathbf{z}$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Adversarial Feature Learning","paper":"/paper/adversarial-feature-learning","first_author":"Jeff Donahue","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/adversarial-feature-learning"},"source":{"url":"http://arxiv.org/abs/1605.09782v7","title":"Adversarial Feature Learning","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/jeffdonahue/bigan","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Self-Supervised Learning","url":"/methods/category/self-supervised-learning","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Adversarial Networks","url":"/methods/category/generative-adversarial-networks","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":15,"archive_num_papers":15,"papers_newest_first":[{"paper":null,"title":"Adventurer: Exploration with BiGAN for Deep Reinforcement Learning","date":"2025-03-24","arxiv_id":"2503.18612","n_code_links":0,"syntology":null},{"paper":"/paper/improving-gans-for-long-tailed-data-through","title":"Improving GANs for Long-Tailed Data through Group Spectral Regularization","date":"2022-08-21","arxiv_id":"2208.09932","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Enhancement to Training of Bidirectional GAN : An Approach to Demystify Tax Fraud","date":"2022-08-16","arxiv_id":"2208.07675","n_code_links":0,"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":null,"title":"Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey","date":"2021-11-26","arxiv_id":"2111.13282","n_code_links":0,"syntology":null},{"paper":"/paper/combining-gans-and-autoencoders-for-efficient","title":"Combining GANs and AutoEncoders for Efficient Anomaly Detection","date":"2020-11-16","arxiv_id":"2011.08102","n_code_links":1,"syntology":null},{"paper":null,"title":"Generalized Adversarially Learned Inference","date":"2020-06-15","arxiv_id":"2006.08089","n_code_links":0,"syntology":null},{"paper":"/paper/bidirectional-generative-modeling-using","title":"Bidirectional Generative Modeling Using Adversarial Gradient Estimation","date":"2020-02-21","arxiv_id":"2002.09161","n_code_links":2,"syntology":null},{"paper":"/paper/surprising-effectiveness-of-few-image","title":"A critical analysis of self-supervision, or what we can learn from a single image","date":"2019-04-30","arxiv_id":"1904.13132","n_code_links":2,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":0}},{"paper":null,"title":"An Empirical Study of Generative Models with Encoders","date":"2018-12-19","arxiv_id":"1812.07909","n_code_links":0,"syntology":null},{"paper":null,"title":"Semi-supervised learning with Bidirectional GANs","date":"2018-11-28","arxiv_id":"1811.11426","n_code_links":0,"syntology":null},{"paper":null,"title":"The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Theoretical limitations of Encoder-Decoder GAN architectures","date":"2017-11-07","arxiv_id":"1711.02651","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-view Generative Adversarial Networks","date":"2016-11-07","arxiv_id":"1611.02019","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-feature-learning","title":"Adversarial Feature Learning","date":"2016-05-31","arxiv_id":"1605.09782","n_code_links":10,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}}],"papers_shown":15,"tasks":[{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/classification","name":"General Classification","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":1},{"task":"/task/density-estimation","name":"Density Estimation","papers":1},{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/face-generation","name":"Face Generation","papers":1},{"task":null,"name":"Generative Adversarial Network","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":1},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":1},{"task":"/task/mujoco","name":"MuJoCo","papers":1},{"task":"/task/outlier-detection","name":"Outlier Detection","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1}],"tasks_shown":20,"n_tasks":28,"usage_by_year":[{"year":"2016","papers":2},{"year":"2017","papers":1},{"year":"2018","papers":3},{"year":"2019","papers":1},{"year":"2020","papers":3},{"year":"2021","papers":2},{"year":"2022","papers":2},{"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/bigan"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}