{"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-binary-autoencoders","title":"Hashing with binary autoencoders","arxiv_id":"1501.00756","date":"2015-01-05","proceeding":"CVPR 2015 6","authors":["Miguel Á. Carreira-Perpiñán","Ramin Raziperchikolaei"],"abstract":"An attractive approach for fast search in image databases is binary hashing,\nwhere each high-dimensional, real-valued image is mapped onto a\nlow-dimensional, binary vector and the search is done in this binary space.\nFinding the optimal hash function is difficult because it involves binary\nconstraints, and most approaches approximate the optimization by relaxing the\nconstraints and then binarizing the result. Here, we focus on the binary\nautoencoder model, which seeks to reconstruct an image from the binary code\nproduced by the hash function. We show that the optimization can be simplified\nwith the method of auxiliary coordinates. This reformulates the optimization as\nalternating two easier steps: one that learns the encoder and decoder\nseparately, and one that optimizes the code for each image. Image retrieval\nexperiments, using precision/recall and a measure of code utilization, show the\nresulting hash function outperforms or is competitive with state-of-the-art\nmethods for binary hashing.","url_abs":"http://arxiv.org/abs/1501.00756v1","url_pdf":"http://arxiv.org/pdf/1501.00756v1.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-binary-autoencoders","repo_url":"https://github.com/CAS-CLab/K-Nearest-Neighbors-Hashing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"hashing-with-binary-autoencoders","repo_url":"https://github.com/HolmesShuan/K-Nearest-Neighbors-Hashing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1501.00756","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}