Papers › TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation

TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation

5 Dec 2024arXiv:2412.04073archive 2025-07-28

A. Enes Doruk, Erhan Oztop, Hasan F. Ates

Unsupervised Domain Adaptation (UDA) aims to utilize labeled data from a source domain to solve tasks in an unlabeled target domain, often hindered by significant domain gaps. Traditional CNN-based methods struggle to fully capture complex domain relationships, motivating the shift to vision transformers like the Swin Transformer, which excel in modeling both local and global dependencies. In this work, we propose a novel UDA approach leveraging the Swin Transformer with three key modules. A Graph Domain Discriminator enhances domain alignment by capturing inter-pixel correlations through graph convolutions and entropy-based attention differentiation. An Adaptive Double Attention module combines Windows and Shifted Windows attention with dynamic reweighting to align long-range and local features effectively. Finally, a Cross-Feature Transform modifies Swin Transformer blocks to improve generalization across domains. Extensive benchmarks confirm the state-of-the-art performance of our versatile method, which requires no task-specific alignment modules, establishing its adaptability to diverse applications.

Paper PDF Code

Code

enesdoruk/TransAdapter officialmentioned 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 Unsupervised Domain Adaptation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Unsupervised Domain Adaptation	DomainNet	Transadapter	Accuracy	53.7	#3 of 4	Archive leaderboard	report
Unsupervised Domain Adaptation	Office-Home	TransAdapter-B	Accuracy	89.4	#3 of 20	Archive leaderboard	report
Unsupervised Domain Adaptation	VisDA-2017	TransAdapter	Accuracy	91.2	#1 of 1	Archive leaderboard	report
Unsupervised Domain Adaptation	VisDA2017	TransAdapter	Accuracy	91.2	#3 of 13	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

ALIGN Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Stochastic Depth Swin Transformer Transformer

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