{"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/category-anchor-guided-unsupervised-domain","title":"Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation","arxiv_id":"1910.13049","date":"2019-10-29","proceeding":"NeurIPS 2019 12","authors":["Qiming Zhang","Jing Zhang","Wei Liu","DaCheng Tao"],"abstract":"Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance since no extra effort is devoted to annotating target domain samples. However, the different data distributions in the two domains, or \\emph{domain shift/discrepancy}, inevitably compromise the UDA performance. Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment. In this paper, we propose a novel category anchor-guided (CAG) UDA model for semantic segmentation, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously. First, the category-wise centroids of the source domain features are used as guided anchors to identify the active features in the target domain and also assign them pseudo-labels. Then, we leverage an anchor-based pixel-level distance loss and a discriminative loss to drive the intra-category features closer and the inter-category features further apart, respectively. Finally, we devise a stagewise training mechanism to reduce the error accumulation and adapt the proposed model progressively. Experiments on both the GTA5$\\rightarrow $Cityscapes and SYNTHIA$\\rightarrow $Cityscapes scenarios demonstrate the superiority of our CAG-UDA model over the state-of-the-art methods. The code is available at \\url{https://github.com/RogerZhangzz/CAG_UDA}.","url_abs":"https://arxiv.org/abs/1910.13049v2","url_pdf":"https://arxiv.org/pdf/1910.13049v2.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":"category-anchor-guided-unsupervised-domain","repo_url":"https://github.com/RogerZhangzz/CAG_UDA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CAG-UDA","rank_in_archive_order":24,"of":28,"metrics":{"mIoU (13 classes)":"44.5"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CAG-UDA","rank_in_archive_order":47,"of":73,"metrics":{"mIoU":"50.2"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CAG-UDA","rank_in_archive_order":33,"of":38,"metrics":{"MIoU (13 classes)":"52.6","MIoU (16 classes)":"44.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.13049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13049"}},"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/RogerZhangzz/CAG_UDA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"05f3653dd76468d9","entry":"get_norm_layer","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/models/networks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05f3653dd76468d9"}},{"code_sha256_prefix":"62a8cdfdb51ec275","entry":"get_scheduler","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/models/networks.py","link_basis":"harvester_set","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":"62a8cdfdb51ec275"}},{"code_sha256_prefix":"bf329cef80ee24c5","entry":"init_net","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/models/networks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf329cef80ee24c5"}},{"code_sha256_prefix":"dfe03b9cbc5639c5","entry":"bootstrapped_cross_entropy2d","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"loss/loss.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/loss/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfe03b9cbc5639c5"}},{"code_sha256_prefix":"57b36a6b7f29df1a","entry":"cross_entropy2d","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"loss/loss.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/loss/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57b36a6b7f29df1a"}},{"code_sha256_prefix":"522eaeb36b99efb4","entry":"grad_reverse","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"models/adaptation_model.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/models/adaptation_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"522eaeb36b99efb4"}},{"code_sha256_prefix":"6ceebb622653f267","entry":"multi_scale_cross_entropy2d","repo":"RogerZhangzz/CAG_UDA","repo_kind":"official","path":"loss/loss.py","file_url":"https://github.com/RogerZhangzz/CAG_UDA/blob/HEAD/loss/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ceebb622653f267"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}