{"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/hashing-with-mutual-information","title":"Hashing with Mutual Information","arxiv_id":"1803.00974","date":"2018-03-02","proceeding":null,"authors":["Fatih Cakir","Kun He","Sarah Adel Bargal","Stan Sclaroff"],"abstract":"Binary vector embeddings enable fast nearest neighbor retrieval in large\ndatabases of high-dimensional objects, and play an important role in many\npractical applications, such as image and video retrieval. We study the problem\nof learning binary vector embeddings under a supervised setting, also known as\nhashing. We propose a novel supervised hashing method based on optimizing an\ninformation-theoretic quantity: mutual information. We show that optimizing\nmutual information can reduce ambiguity in the induced neighborhood structure\nin the learned Hamming space, which is essential in obtaining high retrieval\nperformance. To this end, we optimize mutual information in deep neural\nnetworks with minibatch stochastic gradient descent, with a formulation that\nmaximally and efficiently utilizes available supervision. Experiments on four\nimage retrieval benchmarks, including ImageNet, confirm the effectiveness of\nour method in learning high-quality binary embeddings for nearest neighbor\nretrieval.","url_abs":"http://arxiv.org/abs/1803.00974v2","url_pdf":"http://arxiv.org/pdf/1803.00974v2.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":"hashing-with-mutual-information","repo_url":"https://github.com/fcakir/mihash","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"hashing-with-mutual-information","repo_url":"https://github.com/fcakir/deep-mihash","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}