Papers › Universal Domain Adaptation via Compressive Attention Matching
Universal Domain Adaptation via Compressive Attention Matching
Didi Zhu, Yincuan Li, Junkun Yuan, Zexi Li, Kun Kuang, Chao Wu
Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. The challenge lies in how to determine whether the target samples belong to common categories. The mainstream methods make judgments based on the sample features, which overemphasizes global information while ignoring the most crucial local objects in the image, resulting in limited accuracy. To address this issue, we propose a Universal Attention Matching (UniAM) framework by exploiting the self-attention mechanism in vision transformer to capture the crucial object information. The proposed framework introduces a novel Compressive Attention Matching (CAM) approach to explore the core information by compressively representing attentions. Furthermore, CAM incorporates a residual-based measurement to determine the sample commonness. By utilizing the measurement, UniAM achieves domain-wise and category-wise Common Feature Alignment (CFA) and Target Class Separation (TCS). Notably, UniAM is the first method utilizing the attention in vision transformer directly to perform classification tasks. Extensive experiments show that UniAM outperforms the current state-of-the-art methods on various benchmark datasets.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Universal Domain Adaptation | DomainNet | UniAM | H-Score | 61.52 | #2 of 12 | Archive leaderboard | report |
| Universal Domain Adaptation | DomainNet | UniAM | Source-free | no | #2 of 12 | Archive leaderboard | report |
| Universal Domain Adaptation | Office-31 | UniAM | H-score | 95.95 | #1 of 12 | Archive leaderboard | report |
| Universal Domain Adaptation | Office-31 | UniAM | Source-Free | no | #1 of 12 | Archive leaderboard | report |
| Universal Domain Adaptation | Office-Home | UniAM | H-Score | 81.68 | #2 of 14 | Archive leaderboard | report |
| Universal Domain Adaptation | Office-Home | UniAM | Source-free | no | #2 of 14 | Archive leaderboard | report |
| Universal Domain Adaptation | Office-Home | UniAM | VLM | no | #2 of 14 | Archive leaderboard | report |
| Universal Domain Adaptation | VisDA2017 | UniAM | H-score | 65.18 | #5 of 13 | Archive leaderboard | report |
| Universal Domain Adaptation | VisDA2017 | UniAM | Source-free | no | #5 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
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