{"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/deep-sketch-hashing-fast-free-hand-sketch","title":"Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval","arxiv_id":"1703.05605","date":"2017-03-16","proceeding":"CVPR 2017 7","authors":["Li Liu","Fumin Shen","Yuming Shen","Xianglong Liu","Ling Shao"],"abstract":"Free-hand sketch-based image retrieval (SBIR) is a specific cross-view\nretrieval task, in which queries are abstract and ambiguous sketches while the\nretrieval database is formed with natural images. Work in this area mainly\nfocuses on extracting representative and shared features for sketches and\nnatural images. However, these can neither cope well with the geometric\ndistortion between sketches and images nor be feasible for large-scale SBIR due\nto the heavy continuous-valued distance computation. In this paper, we speed up\nSBIR by introducing a novel binary coding method, named \\textbf{Deep Sketch\nHashing} (DSH), where a semi-heterogeneous deep architecture is proposed and\nincorporated into an end-to-end binary coding framework. Specifically, three\nconvolutional neural networks are utilized to encode free-hand sketches,\nnatural images and, especially, the auxiliary sketch-tokens which are adopted\nas bridges to mitigate the sketch-image geometric distortion. The learned DSH\ncodes can effectively capture the cross-view similarities as well as the\nintrinsic semantic correlations between different categories. To the best of\nour knowledge, DSH is the first hashing work specifically designed for\ncategory-level SBIR with an end-to-end deep architecture. The proposed DSH is\ncomprehensively evaluated on two large-scale datasets of TU-Berlin Extension\nand Sketchy, and the experiments consistently show DSH's superior SBIR\naccuracies over several state-of-the-art methods, while achieving significantly\nreduced retrieval time and memory footprint.","url_abs":"http://arxiv.org/abs/1703.05605v1","url_pdf":"http://arxiv.org/pdf/1703.05605v1.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-sketch-hashing-fast-free-hand-sketch","repo_url":"https://github.com/ymcidence/DeepSketchHashing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.05605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}