Papers › Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

16 Sep 2022arXiv:2209.07695archive 2025-07-28

Lin Chen, Zhixiang Wei, Xin Jin, Huaian Chen, Miao Zheng, Kai Chen, Yi Jin

In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually and softly via various intermediate spaces, dubbed domain bridging (DB). However, for dense prediction tasks such as domain adaptive semantic segmentation (DASS), existing solutions have mostly relied on rough style transfer and how to elegantly bridge domains is still under-explored. In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space. At the heart of DDB lies a dual-path domain bridging step for generating two intermediate domains using the coarse-wise and the fine-wise data mixing techniques, alongside a cross-path knowledge distillation step for taking two complementary models trained on generated intermediate samples as 'teachers' to develop a superior 'student' in a multi-teacher distillation manner. These two optimization steps work in an alternating way and reinforce each other to give rise to DDB with strong adaptation power. Extensive experiments on adaptive segmentation tasks with different settings demonstrate that our DDB significantly outperforms state-of-the-art methods. Code is available at https://github.com/xiaoachen98/DDB.git.

Paper PDF Code

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

Code

xiaoachen98/DDB officialmentioned in papermentioned 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 Adaptation Image-to-Image Translation Knowledge Distillation Semantic Segmentation Style Transfer Synthetic-to-Real Translation Unsupervised Domain Adaptation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Domain Adaptation	GTA5 to Cityscapes	DDB	mIoU	62.7	#14 of 28	Archive leaderboard	report
Domain Adaptation	GTAV to Cityscapes+Mapillary	DDB	mIoU	58.6	#2 of 4	Archive leaderboard	report
Domain Adaptation	GTAV+Synscapes to Cityscapes	DDB	mIoU	69.0	#1 of 6	Archive leaderboard	report
Image-to-Image Translation	GTAV-to-Cityscapes Labels	DDB	mIoU	62.7	#10 of 22	Archive leaderboard	report
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	DDB	mIoU	62.7	#14 of 73	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

Knowledge Distillation

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