{"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/sepico-semantic-guided-pixel-contrast-for","title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","arxiv_id":"2204.08808","date":"2022-04-19","proceeding":null,"authors":["Binhui Xie","Shuang Li","Mingjia Li","Chi Harold Liu","Gao Huang","Guoren Wang"],"abstract":"Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain. In this work, we propose Semantic-Guided Pixel Contrast (SePiCo), a novel one-stage adaptation framework that highlights the semantic concepts of individual pixels to promote learning of class-discriminative and class-balanced pixel representations across domains, eventually boosting the performance of self-training methods. Specifically, to explore proper semantic concepts, we first investigate a centroid-aware pixel contrast that employs the category centroids of the entire source domain or a single source image to guide the learning of discriminative features. Considering the possible lack of category diversity in semantic concepts, we then blaze a trail of distributional perspective to involve a sufficient quantity of instances, namely distribution-aware pixel contrast, in which we approximate the true distribution of each semantic category from the statistics of labeled source data. Moreover, such an optimization objective can derive a closed-form upper bound by implicitly involving an infinite number of (dis)similar pairs, making it computationally efficient. Extensive experiments show that SePiCo not only helps stabilize training but also yields discriminative representations, making significant progress on both synthetic-to-real and daytime-to-nighttime adaptation scenarios.","url_abs":"https://arxiv.org/abs/2204.08808v2","url_pdf":"https://arxiv.org/pdf/2204.08808v2.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":"sepico-semantic-guided-pixel-contrast-for","repo_url":"https://github.com/bit-da/sepico","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","task":"Domain Adaptation","dataset":"GTA5 to Cityscapes","model":"SePiCo","rank_in_archive_order":8,"of":28,"metrics":{"mIoU":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes","task":"Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo","rank_in_archive_order":8,"of":33,"metrics":{"mIoU":"64.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes","task":"Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo (DeepLabv2-ResNet-101)","rank_in_archive_order":14,"of":33,"metrics":{"mIoU":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-gtav-to","task":"Image-to-Image Translation","dataset":"GTAV-to-Cityscapes Labels","model":"SePiCo","rank_in_archive_order":5,"of":22,"metrics":{"mIoU":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo","rank_in_archive_order":4,"of":28,"metrics":{"mIoU (13 classes)":"71.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dark-zurich","task":"Semantic Segmentation","dataset":"Dark Zurich","model":"SePiCo","rank_in_archive_order":6,"of":14,"metrics":{"mIoU":"54.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dark-zurich","task":"Semantic Segmentation","dataset":"Dark Zurich","model":"SePiCo (DeepLab v2 ResNet-101)","rank_in_archive_order":9,"of":14,"metrics":{"mIoU":"45.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-gtav-to-cityscapes-1","task":"Semantic Segmentation","dataset":"GTAV-to-Cityscapes Labels","model":"SePiCo","rank_in_archive_order":4,"of":12,"metrics":{"mIoU":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-synthia-to","task":"Semantic Segmentation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo","rank_in_archive_order":4,"of":7,"metrics":{"Mean IoU":"64.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"SePiCo","rank_in_archive_order":7,"of":73,"metrics":{"mIoU":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"SePiCo - DeepLabv2","rank_in_archive_order":17,"of":73,"metrics":{"mIoU":"61.0"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo","rank_in_archive_order":6,"of":38,"metrics":{"MIoU (13 classes)":"71.4","MIoU (16 classes)":"64.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo (ResNet-101)","rank_in_archive_order":12,"of":38,"metrics":{"MIoU (13 classes)":"66.5","MIoU (16 classes)":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"SePiCo","rank_in_archive_order":7,"of":20,"metrics":{"mIoU":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo","rank_in_archive_order":6,"of":23,"metrics":{"mIoU (13 classes)":"71.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"SePiCo (DeepLabv2 ResNet-101)","rank_in_archive_order":11,"of":23,"metrics":{"mIoU (13 classes)":"66.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.08808","atlas_url":"https://app.syntology.ai/?focus=2204.08808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08808"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/bit-da/sepico","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":1},"by_repo_kind":{},"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":"be78c4e9ca31118d","entry":"calc_grad_magnitude","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":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"be78c4e9ca31118d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}