{"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/deep-supervised-hashing-with-triplet-labels","title":"Deep Supervised Hashing with Triplet Labels","arxiv_id":"1612.03900","date":"2016-12-12","proceeding":null,"authors":["Xiaofang Wang","Yi Shi","Kris M. Kitani"],"abstract":"Hashing is one of the most popular and powerful approximate nearest neighbor\nsearch techniques for large-scale image retrieval. Most traditional hashing\nmethods first represent images as off-the-shelf visual features and then\nproduce hashing codes in a separate stage. However, off-the-shelf visual\nfeatures may not be optimally compatible with the hash code learning procedure,\nwhich may result in sub-optimal hash codes. Recently, deep hashing methods have\nbeen proposed to simultaneously learn image features and hash codes using deep\nneural networks and have shown superior performance over traditional hashing\nmethods. Most deep hashing methods are given supervised information in the form\nof pairwise labels or triplet labels. The current state-of-the-art deep hashing\nmethod DPSH~\\cite{li2015feature}, which is based on pairwise labels, performs\nimage feature learning and hash code learning simultaneously by maximizing the\nlikelihood of pairwise similarities. Inspired by DPSH~\\cite{li2015feature}, we\npropose a triplet label based deep hashing method which aims to maximize the\nlikelihood of the given triplet labels. Experimental results show that our\nmethod outperforms all the baselines on CIFAR-10 and NUS-WIDE datasets,\nincluding the state-of-the-art method DPSH~\\cite{li2015feature} and all the\nprevious triplet label based deep hashing methods.","url_abs":"http://arxiv.org/abs/1612.03900v1","url_pdf":"http://arxiv.org/pdf/1612.03900v1.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":"deep-supervised-hashing-with-triplet-labels","repo_url":"https://github.com/jjmachan/DeepHash","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"deep-hashing","task_name":"Deep Hashing"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.03900","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}