{"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/weakly-supervised-deep-image-hashing-through","title":"Weakly Supervised Deep Image Hashing through Tag Embeddings","arxiv_id":"1806.05804","date":"2018-06-15","proceeding":"CVPR 2019 6","authors":["Vijetha Gattupalli","Yaoxin Zhuo","Baoxin Li"],"abstract":"Many approaches to semantic image hashing have been formulated as supervised\nlearning problems that utilize images and label information to learn the binary\nhash codes. However, large-scale labeled image data is expensive to obtain,\nthus imposing a restriction on the usage of such algorithms. On the other hand,\nunlabelled image data is abundant due to the existence of many Web image\nrepositories. Such Web images may often come with images tags that contain\nuseful information, although raw tags, in general, do not readily lead to\nsemantic labels. Motivated by this scenario, we formulate the problem of\nsemantic image hashing as a weakly-supervised learning problem. We utilize the\ninformation contained in the user-generated tags associated with the images to\nlearn the hash codes. More specifically, we extract the word2vec semantic\nembeddings of the tags and use the information contained in them for\nconstraining the learning. Accordingly, we name our model Weakly Supervised\nDeep Hashing using Tag Embeddings (WDHT). WDHT is tested for the task of\nsemantic image retrieval and is compared against several state-of-art models.\nResults show that our approach sets a new state-of-art in the area of weekly\nsupervised image hashing.","url_abs":"http://arxiv.org/abs/1806.05804v3","url_pdf":"http://arxiv.org/pdf/1806.05804v3.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":"weakly-supervised-deep-image-hashing-through","repo_url":"https://github.com/Vijetha1/WDHT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-hashing","task_name":"Deep Hashing"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.05804","atlas_url":"https://app.syntology.ai/?focus=1806.05804","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}