{"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/domain-adaptation-for-structured-output-via","title":"Domain Adaptation for Structured Output via Discriminative Patch Representations","arxiv_id":"1901.05427","date":"2019-01-16","proceeding":"ICCV 2019 10","authors":["Yi-Hsuan Tsai","Kihyuk Sohn","Samuel Schulter","Manmohan Chandraker"],"abstract":"Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not generalize well to other domains without annotations for model finetuning. To avoid the labor-intensive process of annotation, we develop a domain adaptation method to adapt the source data to the unlabeled target domain. We propose to learn discriminative feature representations of patches in the source domain by discovering multiple modes of patch-wise output distribution through the construction of a clustered space. With such representations as guidance, we use an adversarial learning scheme to push the feature representations of target patches in the clustered space closer to the distributions of source patches. In addition, we show that our framework is complementary to existing domain adaptation techniques and achieves consistent improvements on semantic segmentation. Extensive ablations and results are demonstrated on numerous benchmark datasets with various settings, such as synthetic-to-real and cross-city scenarios.","url_abs":"https://arxiv.org/abs/1901.05427v4","url_pdf":"https://arxiv.org/pdf/1901.05427v4.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":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/wasidennis/AdaptSegNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/KookHoiKim/AdaptSegNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/NiteshBharadwaj/adaptsegnet-materials","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/Sshanu/AdaptSegNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/jizongFox/ReproduceAdaptSegNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/lym29/DASeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/xiaowillow/AdaptSegNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"domain-adaptation-for-structured-output-via","repo_url":"https://github.com/xiaowillow/AdaptSegNet1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"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"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"Discriminative Patch (ResNet-101)","rank_in_archive_order":22,"of":28,"metrics":{"mIoU (13 classes)":"46.5"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"Discriminative Patch","rank_in_archive_order":57,"of":73,"metrics":{"mIoU":"46.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.05427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.05427"}},"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/KookHoiKim/AdaptSegNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lym29/DASeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaowillow/AdaptSegNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wasidennis/AdaptSegNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaowillow/AdaptSegNet1","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NiteshBharadwaj/adaptsegnet-materials","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jizongFox/ReproduceAdaptSegNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Sshanu/AdaptSegNet","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":2,"ran_draft_wrong":2},"by_repo_kind":{"official":{"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":4,"samples":[{"code_sha256_prefix":"21ac171a17099011","entry":"colorize_mask","repo":"wasidennis/AdaptSegNet","repo_kind":"official","path":"pytorch_0.4/evaluate_cityscapes.py","file_url":"https://github.com/wasidennis/AdaptSegNet/blob/HEAD/pytorch_0.4/evaluate_cityscapes.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21ac171a17099011"}},{"code_sha256_prefix":"0e1dfebc19d73e54","entry":"get_feature","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0e1dfebc19d73e54"}},{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":"wasidennis/AdaptSegNet","repo_kind":"official","path":"pytorch_0.4/train_gta2cityscapes_multi.py","file_url":"https://github.com/wasidennis/AdaptSegNet/blob/HEAD/pytorch_0.4/train_gta2cityscapes_multi.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b3b7c1c716f4ca66"}},{"code_sha256_prefix":"ebaa2a398dee9113","entry":"normalize","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ebaa2a398dee9113"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}