Papers › CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation

CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation

27 Aug 2022arXiv:2208.14227archive 2025-07-28

Midhun Vayyat, Jaswin Kasi, Anuraag Bhattacharya, Shuaib Ahmed, Rahul Tallamraju

In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network. More specifically, we extract a multi-level fused-feature map from the encoder, and apply contrastive loss across different classes and different domains, via source-target mixing of images. We consistently improve performance on various feature encoder architectures and for different domain adaptation datasets in semantic segmentation. Furthermore, we introduce a learned-weighted contrastive loss to improve upon on a state-of-the-art multi-resolution training approach in UDA. We produce state-of-the-art results on GTA → Cityscapes (74.4 mIOU, +0.6) and Synthia → Cityscapes (67.2 mIOU, +1.4) datasets. CLUDA effectively demonstrates contrastive learning in UDA as a generic method, which can be easily integrated into any existing UDA for semantic segmentation tasks. Please refer to the supplementary material for the details on implementation.

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

user0407/CLUDA officialmentioned in paperpytorch 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

Contrastive Learning Domain Adaptation Segmentation Semantic Segmentation 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
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	HRDA + CLUDA	mIoU	74.4	#4 of 73	Archive leaderboard	report
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	DAFormer + CLUDA	mIoU	70.11	#8 of 73	Archive leaderboard	report
Synthetic-to-Real Translation	SYNTHIA-to-Cityscapes	CLUDA+HRDA	MIoU (16 classes)	67.2	#4 of 38	Archive leaderboard	report
Unsupervised Domain Adaptation	GTA5-to-Cityscapes	CLUDA+HRDA	mIoU	74.4	#1 of 1	Archive leaderboard	report
Unsupervised Domain Adaptation	GTAV-to-Cityscapes Labels	CLUDA+HRDA	mIoU	74.4	#3 of 20	Archive leaderboard	report
Unsupervised Domain Adaptation	SYNTHIA-to-Cityscapes	CLUDA+HRDA	mIoU	67.2	#22 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.

Methods

Contrastive Learning

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