{"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/conservative-progressive-collaborative","title":"Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation","arxiv_id":"2211.16701","date":"2022-11-30","proceeding":null,"authors":["Siqi Fan","Fenghua Zhu","Zunlei Feng","Yisheng Lv","Mingli Song","Fei-Yue Wang"],"abstract":"Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels. Addressing that, we propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel, and the pseudo supervision is implemented based on both the agreement and disagreement of the two predictions. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision, while the other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity. Thus, the collaboration of conservative evolution and progressive exploration can be achieved. To reduce the influences of the suspicious pseudo labels, the loss is dynamic re-weighted according to the prediction confidence. Extensive experiments demonstrate that CPCL achieves state-of-the-art performance for semi-supervised semantic segmentation.","url_abs":"https://arxiv.org/abs/2211.16701v2","url_pdf":"https://arxiv.org/pdf/2211.16701v2.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":"conservative-progressive-collaborative","repo_url":"https://github.com/leofansq/CPCL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":18,"of":33,"metrics":{"Validation mIoU":"74.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":19,"of":30,"metrics":{"Validation mIoU":"76.98%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":18,"of":23,"metrics":{"Validation mIoU":"78.17%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":17,"of":18,"metrics":{"Validation mIoU":"69.92%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-28","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 183 labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":16,"of":16,"metrics":{"Validation mIoU":"67.02"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"CPCL (DeepLab v3+ with ResNet-101)","rank_in_archive_order":17,"of":27,"metrics":{"Validation mIoU":"77.16"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":24,"of":27,"metrics":{"Validation mIoU":"74.58"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-29","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 366 labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":14,"of":15,"metrics":{"Validation mIoU":"72.14"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"CPCL (DeepLab v3+ with ResNet-101)","rank_in_archive_order":8,"of":14,"metrics":{"Validation mIoU":"77.67%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":12,"of":14,"metrics":{"Validation mIoU":"75.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-30","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 732 labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":16,"of":16,"metrics":{"Validation mIoU":"74.25"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-27","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 92 labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":17,"of":17,"metrics":{"Validation mIoU":"61.88"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-4","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 12.5% labeled","model":"CPCL (DeepLab v3+ with ResNet-101)","rank_in_archive_order":17,"of":38,"metrics":{"Validation mIoU":"76.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-4","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 12.5% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":23,"of":38,"metrics":{"Validation mIoU":"73.74%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-21","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 6.25% labeled","model":"CPCL (DeepLab v3+ with ResNet-101)","rank_in_archive_order":14,"of":19,"metrics":{"Validation mIoU":"73.44"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-21","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 6.25% labeled","model":"CPCL (DeepLab v3+ with ResNet-50)","rank_in_archive_order":16,"of":19,"metrics":{"Validation mIoU":"71.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.16701","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}