{"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/unsupervised-open-domain-recognition-by","title":"Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization","arxiv_id":"1904.08631","date":"2019-04-18","proceeding":"CVPR 2019 6","authors":["Junbao Zhuo","Shuhui Wang","Shuhao Cui","Qingming Huang"],"abstract":"We address the unsupervised open domain recognition (UODR) problem, where\ncategories in labeled source domain S is only a subset of those in unlabeled\ntarget domain T. The task is to correctly classify all samples in T including\nknown and unknown categories. UODR is challenging due to the domain\ndiscrepancy, which becomes even harder to bridge when a large number of unknown\ncategories exist in T. Moreover, the classification rules propagated by graph\nCNN (GCN) may be distracted by unknown categories and lack generalization\ncapability. To measure the domain discrepancy for asymmetric label space\nbetween S and T, we propose Semantic-Guided Matching Discrepancy (SGMD), which\nfirst employs instance matching between S and T, and then the discrepancy is\nmeasured by a weighted feature distance between matched instances. We further\ndesign a limited balance constraint to achieve a more balanced classification\noutput on known and unknown categories. We develop Unsupervised Open Domain\nTransfer Network (UODTN), which learns both the backbone classification network\nand GCN jointly by reducing the SGMD, enforcing the limited balance constraint\nand minimizing the classification loss on S. UODTN better preserves the\nsemantic structure and enforces the consistency between the learned domain\ninvariant visual features and the semantic embeddings. Experimental results\nshow superiority of our method on recognizing images of both known and unknown\ncategories.","url_abs":"http://arxiv.org/abs/1904.08631v1","url_pdf":"http://arxiv.org/pdf/1904.08631v1.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":"unsupervised-open-domain-recognition-by","repo_url":"https://github.com/junbaoZHUO/UODTN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"gcn","method_name":"GCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.08631","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}