Papers › Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation

Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation

10 Nov 2024arXiv:2411.07794archive 2025-07-28

Xiaowei Yu, Zhe Huang, Zao Zhang

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from labeled source domains to improve performance on the unlabeled target domains. While Convolutional Neural Networks (CNNs) have been dominant in previous UDA methods, recent research has shown promise in applying Vision Transformers (ViTs) to this task. In this study, we propose a novel Feature Fusion Transferability Aware Transformer (FFTAT) to enhance ViT performance in UDA tasks. Our method introduces two key innovations: First, we introduce a patch discriminator to evaluate the transferability of patches, generating a transferability matrix. We integrate this matrix into self-attention, directing the model to focus on transferable patches. Second, we propose a feature fusion technique to fuse embeddings in the latent space, enabling each embedding to incorporate information from all others, thereby improving generalization. These two components work in synergy to enhance feature representation learning. Extensive experiments on widely used benchmarks demonstrate that our method significantly improves UDA performance, achieving state-of-the-art (SOTA) results.

Paper PDF Code

Code

Shawey94/WACV2025-FFTAT officialmentioned on GitHubpytorch report

Shawey94/NoisyNN mentioned 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 Representation Learning Unsupervised Domain Adaptation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Domain Adaptation	Office-31	FFTAT	Average Accuracy	96.0	#1 of 40	Archive leaderboard	report
Domain Adaptation	VisDA2017	FFTAT	Accuracy	93.8	#1 of 28	Archive leaderboard	report
Unsupervised Domain Adaptation	Office-Home	FFTAT	Accuracy	91.4	#1 of 20	Archive leaderboard	report
Unsupervised Domain Adaptation	VisDA2017	FFTAT	Accuracy	93.8	#1 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

AWARE Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Focus Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax 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