{"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-discrete-hashing-with-self-supervised","title":"Deep Discrete Hashing with Self-supervised Pairwise Labels","arxiv_id":"1707.02112","date":"2017-07-07","proceeding":null,"authors":["Jingkuan Song","Tao He","Hangbo Fan","Lianli Gao"],"abstract":"Hashing methods have been widely used for applications of large-scale image\nretrieval and classification. Non-deep hashing methods using handcrafted\nfeatures have been significantly outperformed by deep hashing methods due to\ntheir better feature representation and end-to-end learning framework. However,\nthe most striking successes in deep hashing have mostly involved discriminative\nmodels, which require labels. In this paper, we propose a novel unsupervised\ndeep hashing method, named Deep Discrete Hashing (DDH), for large-scale image\nretrieval and classification. In the proposed framework, we address two main\nproblems: 1) how to directly learn discrete binary codes? 2) how to equip the\nbinary representation with the ability of accurate image retrieval and\nclassification in an unsupervised way? We resolve these problems by introducing\nan intermediate variable and a loss function steering the learning process,\nwhich is based on the neighborhood structure in the original space.\nExperimental results on standard datasets (CIFAR-10, NUS-WIDE, and Oxford-17)\ndemonstrate that our DDH significantly outperforms existing hashing methods by\nlarge margin in terms of~mAP for image retrieval and object recognition. Code\nis available at \\url{https://github.com/htconquer/ddh}.","url_abs":"http://arxiv.org/abs/1707.02112v1","url_pdf":"http://arxiv.org/pdf/1707.02112v1.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-discrete-hashing-with-self-supervised","repo_url":"https://github.com/htconquer/ddh","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-hashing","task_name":"Deep Hashing"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}