{"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/optimal-projection-guided-transfer-hashing","title":"Optimal Projection Guided Transfer Hashing for Image Retrieval","arxiv_id":"1903.00252","date":"2019-03-01","proceeding":null,"authors":["Ji Liu","Lei Zhang"],"abstract":"Recently, learning to hash has been widely studied for image retrieval thanks\nto the computation and storage efficiency of binary codes. For most existing\nlearning to hash methods, sufficient training images are required and used to\nlearn precise hashing codes. However, in some real-world applications, there\nare not always sufficient training images in the domain of interest. In\naddition, some existing supervised approaches need a amount of labeled data,\nwhich is an expensive process in term of time, label and human expertise. To\nhandle such problems, inspired by transfer learning, we propose a simple yet\neffective unsupervised hashing method named Optimal Projection Guided Transfer\nHashing (GTH) where we borrow the images of other different but related domain\ni.e., source domain to help learn precise hashing codes for the domain of\ninterest i.e., target domain. Besides, we propose to seek for the maximum\nlikelihood estimation (MLE) solution of the hashing functions of target and\nsource domains due to the domain gap. Furthermore,an alternating optimization\nmethod is adopted to obtain the two projections of target and source domains\nsuch that the domain hashing disparity is reduced gradually. Extensive\nexperiments on various benchmark databases verify that our method outperforms\nmany state-of-the-art learning to hash methods. The implementation details are\navailable at https://github.com/liuji93/GTH.","url_abs":"http://arxiv.org/abs/1903.00252v1","url_pdf":"http://arxiv.org/pdf/1903.00252v1.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":"optimal-projection-guided-transfer-hashing","repo_url":"https://github.com/liuji93/GTH","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}