{"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/context-aware-mixup-for-domain-adaptive","title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","arxiv_id":"2108.03557","date":"2021-08-08","proceeding":null,"authors":["Qianyu Zhou","Zhengyang Feng","Qiqi Gu","Jiangmiao Pang","Guangliang Cheng","Xuequan Lu","Jianping Shi","Lizhuang Ma"],"abstract":"Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation approaches always reduce the domain shifts in pixel level, feature level, and output level. However, almost all of them largely neglect the contextual dependency, which is generally shared across different domains, leading to less-desired performance. In this paper, we propose a novel Context-Aware Mixup (CAMix) framework for domain adaptive semantic segmentation, which exploits this important clue of context-dependency as explicit prior knowledge in a fully end-to-end trainable manner for enhancing the adaptability toward the target domain. Firstly, we present a contextual mask generation strategy by leveraging the accumulated spatial distributions and prior contextual relationships. The generated contextual mask is critical in this work and will guide the context-aware domain mixup on three different levels. Besides, provided the context knowledge, we introduce a significance-reweighted consistency loss to penalize the inconsistency between the mixed student prediction and the mixed teacher prediction, which alleviates the negative transfer of the adaptation, e.g., early performance degradation. Extensive experiments and analysis demonstrate the effectiveness of our method against the state-of-the-art approaches on widely-used UDA benchmarks.","url_abs":"https://arxiv.org/abs/2108.03557v3","url_pdf":"https://arxiv.org/pdf/2108.03557v3.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":"context-aware-mixup-for-domain-adaptive","repo_url":"https://github.com/qianyuzqy/CAMix","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"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"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-gtav-to","task":"Image-to-Image Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CAMix (w DAFormer)","rank_in_archive_order":6,"of":22,"metrics":{"mIoU":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-gtav-to","task":"Image-to-Image Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CAMix (w Deeplabv2 ResNet 101)","rank_in_archive_order":16,"of":22,"metrics":{"mIoU":"55.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CAMix (w DAFormer)","rank_in_archive_order":5,"of":28,"metrics":{"mIoU (13 classes)":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CAMix (w Deeplabv2 ResNet 101)","rank_in_archive_order":12,"of":28,"metrics":{"mIoU (13 classes)":"59.7"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CAMix (w DAFormer)","rank_in_archive_order":9,"of":73,"metrics":{"mIoU":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CAMix (w Deeplabv2 ResNet101)","rank_in_archive_order":29,"of":73,"metrics":{"mIoU":"55.2"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CAMix (w DAFormer)","rank_in_archive_order":34,"of":38,"metrics":{"MIoU (13 classes)":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CAMix (ResNet 101)","rank_in_archive_order":35,"of":38,"metrics":{"MIoU (13 classes)":"59.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"CAMix (w DAFormer)","rank_in_archive_order":8,"of":20,"metrics":{"mIoU":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"CAMix (w Deeplabv2 ResNet 101)","rank_in_archive_order":16,"of":20,"metrics":{"mIoU":"55.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03557"}},"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/qianyuzqy/CAMix","reach":null}],"summary":{"ran_honours":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":"fcbd501f30a007d4","entry":"color_map","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":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fcbd501f30a007d4"}},{"code_sha256_prefix":"799a094d0124a46c","entry":"get_label_vector","repo":"qianyuzqy/CAMix","repo_kind":"official","path":"evaluateUDA.py","file_url":"https://github.com/qianyuzqy/CAMix/blob/HEAD/evaluateUDA.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"799a094d0124a46c"}},{"code_sha256_prefix":"018647a91dc50805","entry":"get_mean_std","repo":"qianyuzqy/CAMix","repo_kind":"official","path":"camix_transforms.py","file_url":"https://github.com/qianyuzqy/CAMix/blob/HEAD/camix_transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"018647a91dc50805"}},{"code_sha256_prefix":"9d6e0a9afb10b95a","entry":"get_iou","repo":"qianyuzqy/CAMix","repo_kind":"official","path":"evaluateUDA.py","file_url":"https://github.com/qianyuzqy/CAMix/blob/HEAD/evaluateUDA.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d6e0a9afb10b95a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}