{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"htconquer/ddh","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4962e10280ed4f7db903b5de6c2695e0172463d5d755dea3fc6ec5744cd02637","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}