Papers › Domain Adaptive and Generalizable Network Architectures and Training Strategies for...

Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation

26 Apr 2023arXiv:2304.13615archive 2025-07-28

Lukas Hoyer, Dengxin Dai, Luc van Gool

Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are mostly based on outdated networks, we benchmark more recent architectures, reveal the potential of Transformers, and design the DAFormer network tailored for UDA&DG. It is enabled by three training strategies to avoid overfitting to the source domain: While (1) Rare Class Sampling mitigates the bias toward common source domain classes, (2) a Thing-Class ImageNet Feature Distance and (3) a learning rate warmup promote feature transfer from ImageNet pretraining. As UDA&DG are usually GPU memory intensive, most previous methods downscale or crop images. However, low-resolution predictions often fail to preserve fine details while models trained with cropped images fall short in capturing long-range, domain-robust context information. Therefore, we propose HRDA, a multi-resolution framework for UDA&DG, that combines the strengths of small high-resolution crops to preserve fine segmentation details and large low-resolution crops to capture long-range context dependencies with a learned scale attention. DAFormer and HRDA significantly improve the state-of-the-art UDA&DG by more than 10 mIoU on 5 different benchmarks. The implementation is available at https://github.com/lhoyer/HRDA.

PaperPDFCode

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

Code

lhoyer/hrda officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
lhoyer/DAFormer mentioned on GitHubpytorchNOASSERTION report
lhoyer/mic mentioned on GitHubpytorch 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

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

Tasks

Domain AdaptationDomain GeneralizationImage SegmentationSemantic SegmentationUnsupervised Domain Adaptation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization GTA-to-Avg(Cityscapes,BDD,Mapillary) HRDA mIoU 55.9 #11 of 24 Archive leaderboard report
Domain Generalization GTA-to-Avg(Cityscapes,BDD,Mapillary) DAFormer mIoU 51.73 #12 of 24 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

fail

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