Papers › Cross-Region Domain Adaptation for Class-level Alignment

Cross-Region Domain Adaptation for Class-level Alignment

14 Sep 2021arXiv:2109.06422archive 2025-07-28

Zhijie Wang, Xing Liu, Masanori Suganuma, Takayuki Okatani

Semantic segmentation requires a lot of training data, which necessitates costly annotation. There have been many studies on unsupervised domain adaptation (UDA) from one domain to another, e.g., from computer graphics to real images. However, there is still a gap in accuracy between UDA and supervised training on native domain data. It is arguably attributable to class-level misalignment between the source and target domain data. To cope with this, we propose a method that applies adversarial training to align two feature distributions in the target domain. It uses a self-training framework to split the image into two regions (i.e., trusted and untrusted), which form two distributions to align in the feature space. We term this approach cross-region adaptation (CRA) to distinguish from the previous methods of aligning different domain distributions, which we call cross-domain adaptation (CDA). CRA can be applied after any CDA method. Experimental results show that this always improves the accuracy of the combined CDA method, having updated the state-of-the-art.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationImage-to-Image TranslationSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation GTA5 to Cityscapes ProDA+CRA mIoU 58.6 #20 of 28 Archive leaderboard report
Domain Adaptation SYNTHIA-to-Cityscapes ProDA+CRA mIoU 56.9 #15 of 33 Archive leaderboard report
Domain Adaptation Synscapes-to-Cityscapes ProDA+CRA mIoU 60.2 #1 of 3 Archive leaderboard report
Image-to-Image Translation GTAV-to-Cityscapes Labels ProDA+CRA mIoU 58.6 #14 of 22 Archive leaderboard report
Image-to-Image Translation SYNTHIA-to-Cityscapes ProDA+CRA mIoU (13 classes) 63.7 #10 of 28 Archive leaderboard report
Semantic Segmentation GTAV-to-Cityscapes Labels ProDA+CRA mIoU 58.6 #9 of 12 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels ProDA + CRA mIoU 58.6 #22 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes ProDA+CRA MIoU (13 classes) 63.7 #14 of 38 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes ProDA+CRA MIoU (16 classes) 56.9 #14 of 38 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.

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