{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bingan-learning-compact-binary-descriptors","title":"BinGAN: Learning Compact Binary Descriptors with a Regularized GAN","arxiv_id":"1806.06778","date":"2018-06-18","proceeding":"NeurIPS 2018 12","authors":["Maciej Zieba","Piotr Semberecki","Tarek El-Gaaly","Tomasz Trzcinski"],"abstract":"In this paper, we propose a novel regularization method for Generative\nAdversarial Networks, which allows the model to learn discriminative yet\ncompact binary representations of image patches (image descriptors). We employ\nthe dimensionality reduction that takes place in the intermediate layers of the\ndiscriminator network and train binarized low-dimensional representation of the\npenultimate layer to mimic the distribution of the higher-dimensional preceding\nlayers. To achieve this, we introduce two loss terms that aim at: (i) reducing\nthe correlation between the dimensions of the binarized low-dimensional\nrepresentation of the penultimate layer i. e. maximizing joint entropy) and\n(ii) propagating the relations between the dimensions in the high-dimensional\nspace to the low-dimensional space. We evaluate the resulting binary image\ndescriptors on two challenging applications, image matching and retrieval, and\nachieve state-of-the-art results.","url_abs":"http://arxiv.org/abs/1806.06778v5","url_pdf":"http://arxiv.org/pdf/1806.06778v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bingan-learning-compact-binary-descriptors","repo_url":"https://github.com/maciejzieba/binGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.06778","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}