{"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/rectifying-pseudo-label-learning-via","title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","arxiv_id":"2003.03773","date":"2020-03-08","proceeding":null,"authors":["Zhedong Zheng","Yi Yang"],"abstract":"This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. Yet the pseudo labels of the target-domain data are usually predicted by the model trained on the source domain. Thus, the generated labels inevitably contain the incorrect prediction due to the discrepancy between the training domain and the test domain, which could be transferred to the final adapted model and largely compromises the training process. To overcome the problem, this paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning for unsupervised semantic segmentation adaptation. Given the input image, the model outputs the semantic segmentation prediction as well as the uncertainty of the prediction. Specifically, we model the uncertainty via the prediction variance and involve the uncertainty into the optimization objective. To verify the effectiveness of the proposed method, we evaluate the proposed method on two prevalent synthetic-to-real semantic segmentation benchmarks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, as well as one cross-city benchmark, i.e., Cityscapes -> Oxford RobotCar. We demonstrate through extensive experiments that the proposed approach (1) dynamically sets different confidence thresholds according to the prediction variance, (2) rectifies the learning from noisy pseudo labels, and (3) achieves significant improvements over the conventional pseudo label learning and yields competitive performance on all three benchmarks.","url_abs":"https://arxiv.org/abs/2003.03773v3","url_pdf":"https://arxiv.org/pdf/2003.03773v3.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":"rectifying-pseudo-label-learning-via","repo_url":"https://github.com/ShigemichiMatsuzaki/MSPL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rectifying-pseudo-label-learning-via","repo_url":"https://github.com/layumi/Seg-Uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","task":"Domain Adaptation","dataset":"GTA5 to Cityscapes","model":"MRNet + Rectifying Label","rank_in_archive_order":25,"of":28,"metrics":{"mIoU":"50.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"MRNet+Rectifying Label","rank_in_archive_order":46,"of":73,"metrics":{"mIoU":"50.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"MRNet+Rectifying Label(ResNet-101)","rank_in_archive_order":26,"of":38,"metrics":{"MIoU (13 classes)":"54.9","MIoU (16 classes)":"47.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-cityscapes-2","task":"Unsupervised Domain Adaptation","dataset":"Cityscapes-to-OxfordCar","model":"MRNet+Rectifying Label(ResNet-101)","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"Uncertainty","rank_in_archive_order":18,"of":20,"metrics":{"mIoU":"50.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"Uncertainty","rank_in_archive_order":19,"of":23,"metrics":{"mIoU":"47.9","mIoU (13 classes)":"54.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.03773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03773"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/layumi/Seg-Uncertainty","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShigemichiMatsuzaki/MSPL","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"21ac171a17099011","entry":"colorize_mask","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"21ac171a17099011"}},{"code_sha256_prefix":"7b5ad493dd203454","entry":"fliplr","repo":"layumi/Seg-Uncertainty","repo_kind":"listed","path":"trainer_ms.py","file_url":"https://github.com/layumi/Seg-Uncertainty/blob/HEAD/trainer_ms.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b5ad493dd203454"}},{"code_sha256_prefix":"8268f08e8daa5d92","entry":"weights_init","repo":"layumi/Seg-Uncertainty","repo_kind":"listed","path":"trainer_ms.py","file_url":"https://github.com/layumi/Seg-Uncertainty/blob/HEAD/trainer_ms.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8268f08e8daa5d92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}