{"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/domain-adaptive-object-detection-via-1","title":"Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment","arxiv_id":null,"date":"2020-10-31","proceeding":null,"authors":["Dang-Khoa Nguyen","Wei-Lun Tseng","Hong-Han Shuai"],"abstract":"Domain adaptation aims to transfer knowledge from the sourcedata with annotations to scarcely-labeled data in the target domain,which has attracted a lot of attention in recent years and facilitatedmany multimedia applications. Recent approaches have shown theeffectiveness of using adversarial learning to reduce the distribu-tion discrepancy between the source and target images by aligningdistribution between source and target images at both image and in-stance levels. However, this remains challenging since two domainsmay have distinct background scenes and different objects. More-over, complex combinations of objects and a variety of image stylesdeteriorate the unsupervised cross-domain distribution alignment.To address these challenges, in this paper, we design an end-to-endapproach for unsupervised domain adaptation of object detector.Specifically, we propose a Multi-level Entropy Attention Alignment(MEAA) method that consists of two main components: (1) LocalUncertainty Attentional Alignment (LUAA) module to acceleratethe model better perceiving structure-invariant objects of interestby utilizing information theory to measure the uncertainty of eachlocal region via the entropy of the pixel-wise domain classifierand (2) Multi-level Uncertainty-Aware Context Alignment (MUCA)module to enrich domain-invariant information of relevant objectsbased on the entropy of multi-level domain classifiers. The proposedMEAA is evaluated in four domain-shift object detection scenarios.Experiment results demonstrate state-of-the-art performance onthree challenging scenarios and competitive performance on onebenchmark dataset.","url_abs":"https://dl.acm.org/doi/10.1145/3394171.3413553","url_pdf":"https://dl.acm.org/doi/pdf/10.1145/3394171.3413553","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":"domain-adaptive-object-detection-via-1","repo_url":"https://github.com/basiclab/DA-OD-MEAA-PyTorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"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-6","task":"Weakly Supervised Object Detection","dataset":"Cityscapes-to-Foggy Cityscapes","model":"MEAA","rank_in_archive_order":1,"of":2,"metrics":{"mAP":"40.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-2","task":"Weakly Supervised Object Detection","dataset":"Clipart1k","model":"MEAA","rank_in_archive_order":6,"of":7,"metrics":{"MAP":"41.1"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-object-detection-on-1","task":"Weakly Supervised Object Detection","dataset":"Watercolor2k","model":"MEAA","rank_in_archive_order":8,"of":12,"metrics":{"MAP":"55.5"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}