{"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/informative-and-consistent-correspondence","title":"Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection","arxiv_id":null,"date":"2021-06-19","proceeding":"CVPR 2021 1","authors":["Luwei Hou","Yu Zhang","Kui Fu","Jia Li"],"abstract":"    Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i.e. with object bounding boxes) to train object detectors for target domains that are weakly labeled (i.e. with image-level tags). Instead of domain-level distribution matching, as popularly adopted in the literature, we propose to learn pixel-wise cross-domain correspondences for more precise knowledge transfer. It is realized through a novel cross-domain co-attention scheme trained as region competition. In this scheme, the cross-domain correspondence module seeks for informative features on the target domain image, which after being warped to the source domain image, could best explain its annotations. Meanwhile, a collaborative mask generator competes to mask out the relevant target image region to make the remaining features uninformative. Such competitive learning strives to correlate the full foreground in cross-domain image pairs, revealing the accurate object extent in target domain. To alleviate the ambiguity of inter-domain correspondence learning, a domain-cycle consistency regularizer is futher proposed to leverage the more reliable intra-domain correspondence. The proposed approach achieves consistent improvements over existing approaches by a considerable margin, demonstrated by the experiments on various datasets.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2021/html/Hou_Informative_and_Consistent_Correspondence_Mining_for_Cross-Domain_Weakly_Supervised_Object_CVPR_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2021/papers/Hou_Informative_and_Consistent_Correspondence_Mining_for_Cross-Domain_Weakly_Supervised_Object_CVPR_2021_paper.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":[],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-2","task":"Weakly Supervised Object Detection","dataset":"Clipart1k","model":"ICCM","rank_in_archive_order":4,"of":7,"metrics":{"MAP":"46.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-comic2k","task":"Weakly Supervised Object Detection","dataset":"Comic2k","model":"ICCM","rank_in_archive_order":7,"of":8,"metrics":{"MAP":"37.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-1","task":"Weakly Supervised Object Detection","dataset":"Watercolor2k","model":"ICCM","rank_in_archive_order":6,"of":12,"metrics":{"MAP":"57.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}