{"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-class-wise-hashing-semantics-preserving","title":"Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss","arxiv_id":"1803.04137","date":"2018-03-12","proceeding":null,"authors":["Xuefei Zhe","Shifeng Chen","Hong Yan"],"abstract":"Deep supervised hashing has emerged as an influential solution to large-scale\nsemantic image retrieval problems in computer vision. In the light of recent\nprogress, convolutional neural network based hashing methods typically seek\npair-wise or triplet labels to conduct the similarity preserving learning.\nHowever, complex semantic concepts of visual contents are hard to capture by\nsimilar/dissimilar labels, which limits the retrieval performance. Generally,\npair-wise or triplet losses not only suffer from expensive training costs but\nalso lack in extracting sufficient semantic information. In this regard, we\npropose a novel deep supervised hashing model to learn more compact class-level\nsimilarity preserving binary codes. Our deep learning based model is motivated\nby deep metric learning that directly takes semantic labels as supervised\ninformation in training and generates corresponding discriminant hashing code.\nSpecifically, a novel cubic constraint loss function based on Gaussian\ndistribution is proposed, which preserves semantic variations while penalizes\nthe overlap part of different classes in the embedding space. To address the\ndiscrete optimization problem introduced by binary codes, a two-step\noptimization strategy is proposed to provide efficient training and avoid the\nproblem of gradient vanishing. Extensive experiments on four large-scale\nbenchmark databases show that our model can achieve the state-of-the-art\nretrieval performance. Moreover, when training samples are limited, our method\nsurpasses other supervised deep hashing methods with non-negligible margins.","url_abs":"http://arxiv.org/abs/1803.04137v1","url_pdf":"http://arxiv.org/pdf/1803.04137v1.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-class-wise-hashing-semantics-preserving","repo_url":"https://github.com/mzhang367/dcwh","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-hashing","task_name":"Deep Hashing"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"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":"mzhang367/dcwh","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":"9d2d314381ec659a9eaba64229e8e3b5351fa2560803b3830f13b1443b474e7e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}