{"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/single-domain-generalized-object-detection-in","title":"Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation","arxiv_id":null,"date":"2022-01-01","proceeding":"CVPR 2022 1","authors":["Aming Wu","Cheng Deng"],"abstract":"    In this paper, we are concerned with enhancing the generalization capability of object detectors. And we consider a realistic yet challenging scenario, namely Single-Domain Generalized Object Detection (Single-DGOD), which aims to learn an object detector that performs well on many unseen target domains with only one source domain for training. Towards Single-DGOD, it is important to extract domain-invariant representations (DIR) containing intrinsical object characteristics, which is beneficial for improving the robustness for unseen domains. Thus, we present a method, i.e., cyclic-disentangled self-distillation, to disentangle DIR from domain-specific representations without the supervision of domain-related annotations (e.g., domain labels). Concretely, a cyclic-disentangled module is first proposed to cyclically extract DIR from the input visual features. Through the cyclic operation, the disentangled ability can be promoted without the reliance on domain-related annotations. Then, taking the DIR as the teacher, we design a self-distillation module to further enhance the generalization ability. In the experiments, our method is evaluated in urban-scene object detection. Experimental results of five weather conditions show that our method obtains a significant performance gain over baseline methods. Particularly, for the night-sunny scene, our method outperforms baselines by 3%, which indicates that our method is instrumental in enhancing generalization ability. Data and code are available at https://github.com/AmingWu/Single-DGOD.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2022/html/Wu_Single-Domain_Generalized_Object_Detection_in_Urban_Scene_via_Cyclic-Disentangled_Self-Distillation_CVPR_2022_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2022/papers/Wu_Single-Domain_Generalized_Object_Detection_in_Urban_Scene_via_Cyclic-Disentangled_Self-Distillation_CVPR_2022_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":[{"paper_slug":"single-domain-generalized-object-detection-in","repo_url":"https://github.com/amingwu/single-dgod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"robust-object-detection","task_name":"Robust Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"dwd","name":"DWD","full_name":"Diverse Weather Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/robust-object-detection-on-dwd","task":"Robust Object Detection","dataset":"DWD","model":"CDSD","rank_in_archive_order":7,"of":12,"metrics":{"mPC [AP50]":"28.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}