{"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/dual-asymmetric-deep-hashing-learning","title":"Dual Asymmetric Deep Hashing Learning","arxiv_id":"1801.08360","date":"2018-01-25","proceeding":null,"authors":["Jinxing Li","Bob Zhang","Guangming Lu","David Zhang"],"abstract":"Due to the impressive learning power, deep learning has achieved a remarkable\nperformance in supervised hash function learning. In this paper, we propose a\nnovel asymmetric supervised deep hashing method to preserve the semantic\nstructure among different categories and generate the binary codes\nsimultaneously. Specifically, two asymmetric deep networks are constructed to\nreveal the similarity between each pair of images according to their semantic\nlabels. The deep hash functions are then learned through two networks by\nminimizing the gap between the learned features and discrete codes.\nFurthermore, since the binary codes in the Hamming space also should keep the\nsemantic affinity existing in the original space, another asymmetric pairwise\nloss is introduced to capture the similarity between the binary codes and\nreal-value features. This asymmetric loss not only improves the retrieval\nperformance, but also contributes to a quick convergence at the training phase.\nBy taking advantage of the two-stream deep structures and two types of\nasymmetric pairwise functions, an alternating algorithm is designed to optimize\nthe deep features and high-quality binary codes efficiently. Experimental\nresults on three real-world datasets substantiate the effectiveness and\nsuperiority of our approach as compared with state-of-the-art.","url_abs":"http://arxiv.org/abs/1801.08360v1","url_pdf":"http://arxiv.org/pdf/1801.08360v1.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":"dual-asymmetric-deep-hashing-learning","repo_url":"https://github.com/deepakks1995/DeepHashing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-hashing","task_name":"Deep Hashing"},{"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"},"arxiv_metadata":null,"syntology_extracted_results":null}