{"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/zero-shot-sketch-image-hashing","title":"Zero-Shot Sketch-Image Hashing","arxiv_id":"1803.02284","date":"2018-03-06","proceeding":"CVPR 2018 6","authors":["Yuming Shen","Li Liu","Fumin Shen","Ling Shao"],"abstract":"Recent studies show that large-scale sketch-based image retrieval (SBIR) can\nbe efficiently tackled by cross-modal binary representation learning methods,\nwhere Hamming distance matching significantly speeds up the process of\nsimilarity search. Providing training and test data subjected to a fixed set of\npre-defined categories, the cutting-edge SBIR and cross-modal hashing works\nobtain acceptable retrieval performance. However, most of the existing methods\nfail when the categories of query sketches have never been seen during\ntraining. In this paper, the above problem is briefed as a novel but realistic\nzero-shot SBIR hashing task. We elaborate the challenges of this special task\nand accordingly propose a zero-shot sketch-image hashing (ZSIH) model. An\nend-to-end three-network architecture is built, two of which are treated as the\nbinary encoders. The third network mitigates the sketch-image heterogeneity and\nenhances the semantic relations among data by utilizing the Kronecker fusion\nlayer and graph convolution, respectively. As an important part of ZSIH, we\nformulate a generative hashing scheme in reconstructing semantic knowledge\nrepresentations for zero-shot retrieval. To the best of our knowledge, ZSIH is\nthe first zero-shot hashing work suitable for SBIR and cross-modal search.\nComprehensive experiments are conducted on two extended datasets, i.e., Sketchy\nand TU-Berlin with a novel zero-shot train-test split. The proposed model\nremarkably outperforms related works.","url_abs":"http://arxiv.org/abs/1803.02284v1","url_pdf":"http://arxiv.org/pdf/1803.02284v1.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":"zero-shot-sketch-image-hashing","repo_url":"https://github.com/ymcidence/Zero-Shot-Sketch-Image-Hashing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.02284","atlas_url":"https://app.syntology.ai/?focus=1803.02284","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}