</> Code with Papers by Syntology

Papers › G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation

G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation

7 Sep 2022KES 2022 9archive 2025-07-28

Nguyen Viet Manh, Kieu Dang Nam, Dinh Viet Sang, Thi-Oanh Nguyen

Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a source dataset with dense pixel-level annotations to an unlabeled target dataset. However, the performance of UDA methods often suffers from the domain shift, which is the discrepancy between the feature distributions of the two domains. There have been several attempts to match these distributions at the image level marginally. However, due to the so-called category-level domain shift, such global alignments do not guarantee a good separability of deep features extracted from different categories in the target domain. As a result, the generated pseudo-labels can be noisy and thus poison the learning process on the target domain. Some recent methods focus on denoising the pseudo-labels online using category-wise information. This paper introduces a novel UDA method called Global-to-Local alignment (G2L) that leverages fine-grained adversarial training and a newly proposed chromatic Fourier transform to address the image-level domain shift from a global perspective. Next, our method deals with the category-level domain shift under a local view. Specifically, we propose a long-tail category rating strategy as well as apply dynamic confidence thresholds and category-wise priority weights when generating and denoising the pseudo-labels to favor rare categories. Finally, self-distillation is used to boost the final segmentation results. Experiments on popular benchmarks GTA5 → Cityscapes and SYNTHIA → Cityscapes show that our method yields superior accuracy performance than other state-of-the-art methods.

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

DenoisingDomain 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 G2L mIoU 59.7 #18 of 28 Archive leaderboard report
Image-to-Image Translation GTAV-to-Cityscapes Labels G2L mIoU 59.7 #13 of 22 Archive leaderboard report
Semantic Segmentation GTAV-to-Cityscapes Labels G2L mIoU 59.7 #8 of 12 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels G2L mIoU 59.7 #19 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes G2L MIoU (13 classes) 64.4 #15 of 38 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes G2L MIoU (16 classes) 56.8 #15 of 38 Archive leaderboard report
Unsupervised Domain Adaptation GTAV-to-Cityscapes Labels G2L mIoU 59.7 #13 of 20 Archive leaderboard report
Unsupervised Domain Adaptation SYNTHIA-to-Cityscapes G2L mIoU 56.8 #13 of 23 Archive leaderboard report
Unsupervised Domain Adaptation SYNTHIA-to-Cityscapes G2L mIoU (13 classes) 64.4 #13 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.

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