{"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/smoothing-matters-momentum-transformer-for","title":"Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation","arxiv_id":"2203.07988","date":"2022-03-15","proceeding":null,"authors":["Runfa Chen","Yu Rong","Shangmin Guo","Jiaqi Han","Fuchun Sun","Tingyang Xu","Wenbing Huang"],"abstract":"After the great success of Vision Transformer variants (ViTs) in computer vision, it has also demonstrated great potential in domain adaptive semantic segmentation. Unfortunately, straightforwardly applying local ViTs in domain adaptive semantic segmentation does not bring in expected improvement. We find that the pitfall of local ViTs is due to the severe high-frequency components generated during both the pseudo-label construction and features alignment for target domains. These high-frequency components make the training of local ViTs very unsmooth and hurt their transferability. In this paper, we introduce a low-pass filtering mechanism, momentum network, to smooth the learning dynamics of target domain features and pseudo labels. Furthermore, we propose a dynamic of discrepancy measurement to align the distributions in the source and target domains via dynamic weights to evaluate the importance of the samples. After tackling the above issues, extensive experiments on sim2real benchmarks show that the proposed method outperforms the state-of-the-art methods. Our codes are available at https://github.com/alpc91/TransDA","url_abs":"https://arxiv.org/abs/2203.07988v1","url_pdf":"https://arxiv.org/pdf/2203.07988v1.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":"smoothing-matters-momentum-transformer-for","repo_url":"https://github.com/alpc91/transda","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":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"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"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","task":"Domain Adaptation","dataset":"GTA5 to Cityscapes","model":"TransDA-B","rank_in_archive_order":13,"of":28,"metrics":{"mIoU":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-gtav-to","task":"Image-to-Image Translation","dataset":"GTAV-to-Cityscapes Labels","model":"TransDA-B","rank_in_archive_order":9,"of":22,"metrics":{"mIoU":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"TransDA-B","rank_in_archive_order":8,"of":28,"metrics":{"mIoU (13 classes)":"66.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-gtav-to-cityscapes-1","task":"Semantic Segmentation","dataset":"GTAV-to-Cityscapes Labels","model":"TransDA-B","rank_in_archive_order":7,"of":12,"metrics":{"mIoU":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-synthia-to","task":"Semantic Segmentation","dataset":"SYNTHIA-to-Cityscapes","model":"TransDA-B","rank_in_archive_order":7,"of":7,"metrics":{"Mean IoU":"59.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"TransDA-B","rank_in_archive_order":13,"of":73,"metrics":{"mIoU":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"TransDA-B","rank_in_archive_order":11,"of":38,"metrics":{"MIoU (13 classes)":"66.3","MIoU (16 classes)":"59.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"TransDA-B","rank_in_archive_order":11,"of":20,"metrics":{"mIoU":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"TransDA-B","rank_in_archive_order":12,"of":23,"metrics":{"mIoU (13 classes)":"66.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.07988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07988"}},"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/alpc91/transda","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","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":"61bf152e6a42a184"}},{"code_sha256_prefix":"b62c4cc79bbeaff7","entry":"accuracy","repo":"alpc91/transda","repo_kind":"official","path":"core/models/accuracy.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/models/accuracy.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":"b62c4cc79bbeaff7"}},{"code_sha256_prefix":"eede9b1fe3941d7c","entry":"build_adversarial_discriminator_cls","repo":"alpc91/transda","repo_kind":"official","path":"core/models/build.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/models/build.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":"eede9b1fe3941d7c"}},{"code_sha256_prefix":"103a888fd28034bf","entry":"build_classifier","repo":"alpc91/transda","repo_kind":"official","path":"core/models/build.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/models/build.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":"103a888fd28034bf"}},{"code_sha256_prefix":"2f921ad8e71df973","entry":"build_dataset","repo":"alpc91/transda","repo_kind":"official","path":"core/datasets/build.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/datasets/build.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":"2f921ad8e71df973"}},{"code_sha256_prefix":"2afafd3f3ccafc70","entry":"build_feature_extractor","repo":"alpc91/transda","repo_kind":"official","path":"core/models/build.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/models/build.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":"2afafd3f3ccafc70"}},{"code_sha256_prefix":"025b807a1a19d500","entry":"build_transform","repo":"alpc91/transda","repo_kind":"official","path":"core/datasets/build.py","file_url":"https://github.com/alpc91/transda/blob/HEAD/core/datasets/build.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":"025b807a1a19d500"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}