Papers › Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

17 Jul 2020ECCV 2020 8arXiv:2007.09222archive 2025-07-28

Haoran Wang, Tong Shen, Wei zhang, Ling-Yu Duan, Tao Mei

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain. However, most existing methods attempt to perform the alignment from a holistic view, ignoring the underlying class-level data structure in the target domain. To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains. We adopt a fine-grained domain discriminator that not only plays as a domain distinguisher, but also differentiates domains at class level. The traditional binary domain labels are also generalized to domain encodings as the supervision signal to guide the fine-grained feature alignment. An analysis with Class Center Distance (CCD) validates that our fine-grained adversarial strategy achieves better class-level alignment compared to other state-of-the-art methods. Our method is easy to implement and its effectiveness is evaluated on three classical domain adaptation tasks, i.e., GTA5 to Cityscapes, SYNTHIA to Cityscapes and Cityscapes to Cross-City. Large performance gains show that our method outperforms other global feature alignment based and class-wise alignment based counterparts. The code is publicly available at https://github.com/JDAI-CV/FADA.

PaperPDFConference PDFCode

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

Code

JDAI-CV/FADA officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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 AdaptationImage-to-Image TranslationSemantic SegmentationSynthetic-to-Real Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation SYNTHIA-to-Cityscapes FADA (ResNet-101) mIoU 45.2 #24 of 33 Archive leaderboard report
Domain Adaptation SYNTHIA-to-Cityscapes FADA (VGG-16) mIoU 39.5 #31 of 33 Archive leaderboard report
Image-to-Image Translation SYNTHIA-to-Cityscapes FADA (ResNet-101) mIoU (13 classes) 52.5 #15 of 28 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels FADA mIoU 50.1 #48 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes FADA(ResNet-101) MIoU (13 classes) 52.5 #31 of 38 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes FADA(ResNet-101) MIoU (16 classes) 45.2 #31 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