{"url":"/method/infogan","slug":"infogan","name":"InfoGAN","full_name":"InfoGAN","full_name_withheld":false,"description_markdown":"**InfoGAN** is a type of generative adversarial network that modifies the [GAN](https://paperswithcode.com/method/gan) objective to\r\nencourage it to learn interpretable and meaningful representations. This is done by maximizing the\r\nmutual information between a fixed small subset of the GAN’s noise variables and the observations.\r\n\r\nFormally, InfoGAN is defined as a minimax game with a variational regularization of mutual information and the hyperparameter $\\lambda$:\r\n\r\n$$ \\min\\_{G, Q}\\max\\_{D}V\\_{INFOGAN}\\left(D, G, Q\\right) = V\\left(D, G\\right) - \\lambda{L}\\_{I}\\left(G, Q\\right) $$\r\n\r\nWhere $Q$ is an auxiliary distribution that approximates the posterior $P\\left(c\\mid{x}\\right)$ - the probability of the latent code $c$ given the data $x$ - and $L\\_{I}$ is the variational lower bound of the mutual information between the latent code and the observations.\r\n\r\nIn the practical implementation, there is another fully-connected layer to output parameters for the conditional distribution $Q$ (negligible computation ontop of regular GAN structures). Q is represented with a [softmax](https://paperswithcode.com/method/softmax) non-linearity for a categorical latent code. For a continuous latent code, the authors assume a factored Gaussian.","description_state":"present","introduced_year":null,"introduced_by":{"title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","paper":"/paper/infogan-interpretable-representation-learning","first_author":"Xi Chen","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/infogan-interpretable-representation-learning"},"source":{"url":"http://arxiv.org/abs/1606.03657v1","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/eriklindernoren/PyTorch-GAN/blob/master/implementations/infogan/infogan.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":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":35,"archive_num_papers":35,"papers_newest_first":[{"paper":null,"title":"Generative Adversarial Networks Bridging Art and Machine Intelligence","date":"2025-02-06","arxiv_id":"2502.04116","n_code_links":0,"syntology":null},{"paper":null,"title":"Unsupervised and Interpretable Synthesizing for Electrical Time Series Based on Information Maximizing Generative Adversarial Nets","date":"2024-07-18","arxiv_id":"2407.13691","n_code_links":0,"syntology":null},{"paper":"/paper/comparing-information-content-of","title":"Comparing the information content of probabilistic representation spaces","date":"2024-05-31","arxiv_id":"2405.21042","n_code_links":1,"syntology":null},{"paper":"/paper/double-infogan-for-contrastive-analysis","title":"Double InfoGAN for Contrastive Analysis","date":"2024-01-31","arxiv_id":"2401.17776","n_code_links":1,"syntology":null},{"paper":null,"title":"GAN-GA: A Generative Model based on Genetic Algorithm for Medical Image Generation","date":"2023-12-30","arxiv_id":"2401.00314","n_code_links":0,"syntology":null},{"paper":"/paper/fusing-conditional-submodular-gan-and","title":"Fusing Conditional Submodular GAN and Programmatic Weak Supervision","date":"2023-12-16","arxiv_id":"2312.10366","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":null,"title":"The objective function equality property of infoGAN for two-layer network","date":"2023-09-30","arxiv_id":"2310.00443","n_code_links":0,"syntology":null},{"paper":"/paper/hsic-infogan-learning-unsupervised","title":"HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information","date":"2022-08-06","arxiv_id":"2208.03563","n_code_links":1,"syntology":null},{"paper":null,"title":"k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension","date":"2022-06-17","arxiv_id":"2206.08526","n_code_links":0,"syntology":null},{"paper":null,"title":"Analytical Interpretation of Latent Codes in InfoGAN with SAR Images","date":"2022-05-26","arxiv_id":"2205.13294","n_code_links":0,"syntology":null},{"paper":null,"title":"LatentGAN Autoencoder: Learning Disentangled Latent Distribution","date":"2022-04-05","arxiv_id":"2204.02010","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-fine-grained-class-clustering-via-1","title":"Contrastive Fine-grained Class Clustering via Generative Adversarial Networks","date":"2021-12-30","arxiv_id":"2112.14971","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":3}},{"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":null,"title":"Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion","date":"2021-10-02","arxiv_id":"2110.00788","n_code_links":0,"syntology":null},{"paper":null,"title":"ADIS-GAN: Affine Disentangled GAN","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Representation Decomposition for Image Manipulation and Beyond","date":"2020-11-02","arxiv_id":"2011.00788","n_code_links":0,"syntology":null},{"paper":null,"title":"DPD-InfoGAN: Differentially Private Distributed InfoGAN","date":"2020-10-22","arxiv_id":"2010.11398","n_code_links":0,"syntology":null},{"paper":"/paper/ciwgan-and-fiwgan-encoding-information-in","title":"CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks","date":"2020-06-04","arxiv_id":"2006.02951","n_code_links":1,"syntology":null},{"paper":"/paper/disentanglement-based-active-learning","title":"Disentanglement based Active Learning","date":"2019-12-15","arxiv_id":"1912.07018","n_code_links":1,"syntology":null},{"paper":null,"title":"Towards Better Understanding of Disentangled Representations via Mutual Information","date":"2019-11-25","arxiv_id":"1911.10922","n_code_links":0,"syntology":null},{"paper":null,"title":"Generative Adversarial Networks for Failure Prediction","date":"2019-10-04","arxiv_id":"1910.02034","n_code_links":0,"syntology":null},{"paper":"/paper/elastic-infogan-unsupervised-disentangled","title":"Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data","date":"2019-10-01","arxiv_id":"1910.01112","n_code_links":1,"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/maximizing-mutual-information-for-tacotron","title":"Maximizing Mutual Information for Tacotron","date":"2019-08-30","arxiv_id":"1909.01145","n_code_links":2,"syntology":null},{"paper":null,"title":"Unsupervised Classification of Street Architectures Based on InfoGAN","date":"2019-05-30","arxiv_id":"1905.12844","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning Robotic Manipulation through Visual Planning and Acting","date":"2019-05-11","arxiv_id":"1905.04411","n_code_links":0,"syntology":null},{"paper":"/paper/ib-gan-disentangled-representation-learning","title":"IB-GAN: Disentangled Representation Learning with Information Bottleneck GAN","date":"2019-05-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/social-ways-learning-multi-modal","title":"Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs","date":"2019-04-20","arxiv_id":"1904.09507","n_code_links":1,"syntology":null},{"paper":"/paper/heartbeat-anomaly-detection-using-adversarial","title":"Heartbeat Anomaly Detection using Adversarial Oversampling","date":"2019-01-28","arxiv_id":"1901.09972","n_code_links":1,"syntology":null},{"paper":null,"title":"Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning","date":"2018-01-26","arxiv_id":"1801.08712","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/disentanglement","name":"Disentanglement","papers":9},{"task":null,"name":"Generative Adversarial Network","papers":6},{"task":"/task/image-generation","name":"Image Generation","papers":6},{"task":"/task/representation-learning","name":"Representation Learning","papers":4},{"task":"/task/attribute","name":"Attribute","papers":3},{"task":"/task/classification","name":"General Classification","papers":3},{"task":"/task/clustering","name":"Clustering","papers":2},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":2},{"task":"/task/text-to-image-generation","name":"Text-to-Image Generation","papers":2},{"task":"/task/translation","name":"Translation","papers":2},{"task":"/task/unsupervised-image-classification","name":"Unsupervised Image Classification","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/active-learning","name":"Active Learning","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1}],"tasks_shown":20,"n_tasks":50,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":3},{"year":"2018","papers":2},{"year":"2019","papers":11},{"year":"2020","papers":3},{"year":"2021","papers":4},{"year":"2022","papers":4},{"year":"2023","papers":3},{"year":"2024","papers":3},{"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/infogan"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}