Papers › Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation

Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation

15 Mar 2022arXiv:2203.07988archive 2025-07-28

Runfa Chen, Yu Rong, Shangmin Guo, Jiaqi Han, Fuchun Sun, Tingyang Xu, Wenbing Huang

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

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.07988")

Code

Syntology Ran 2 of 8 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 6 samples from 1 repository, 0 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alpc91/transda officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 2 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
6unverified

Licence: 2 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from alpc91/transda. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

accuracy alpc91/transda/core/models/accuracy.py official repository unverified MIT (permissive) · b62c4cc79bbeaff7 · report
build_adversarial_discriminator_cls alpc91/transda/core/models/build.py official repository unverified MIT (permissive) · eede9b1fe3941d7c · report
build_classifier alpc91/transda/core/models/build.py official repository unverified MIT (permissive) · 103a888fd28034bf · report
build_dataset alpc91/transda/core/datasets/build.py official repository unverified MIT (permissive) · 2f921ad8e71df973 · report
build_feature_extractor alpc91/transda/core/models/build.py official repository unverified MIT (permissive) · 2afafd3f3ccafc70 · report
build_transform alpc91/transda/core/datasets/build.py official repository unverified MIT (permissive) · 025b807a1a19d500 · report
window_partition identical code first harvested elsewhere ran · fixture could not drive it fingerprinted licence of this copy not recorded · 144d10b49baeb8a6 · report
window_reverse identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 61bf152e6a42a184 · report

Tasks

Domain AdaptationImage-to-Image TranslationPseudo LabelSegmentationSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation GTA5 to Cityscapes TransDA-B mIoU 63.9 #13 of 28 Archive leaderboard report
Image-to-Image Translation GTAV-to-Cityscapes Labels TransDA-B mIoU 63.9 #9 of 22 Archive leaderboard report
Image-to-Image Translation SYNTHIA-to-Cityscapes TransDA-B mIoU (13 classes) 66.3 #8 of 28 Archive leaderboard report
Semantic Segmentation GTAV-to-Cityscapes Labels TransDA-B mIoU 63.9 #7 of 12 Archive leaderboard report
Semantic Segmentation SYNTHIA-to-Cityscapes TransDA-B Mean IoU 59.3 #7 of 7 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels TransDA-B mIoU 63.9 #13 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes TransDA-B MIoU (13 classes) 66.3 #11 of 38 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes TransDA-B MIoU (16 classes) 59.3 #11 of 38 Archive leaderboard report
Unsupervised Domain Adaptation GTAV-to-Cityscapes Labels TransDA-B mIoU 63.9 #11 of 20 Archive leaderboard report
Unsupervised Domain Adaptation SYNTHIA-to-Cityscapes TransDA-B mIoU (13 classes) 66.3 #12 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections