Papers › Towards Unified and Effective Domain Generalization
Towards Unified and Effective Domain Generalization
Yiyuan Zhang, Kaixiong Gong, Xiaohan Ding, Kaipeng Zhang, Fangrui Lv, Kurt Keutzer, Xiangyu Yue
We propose UniDG, a novel and Unified framework for Domain Generalization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of their architectures. The core idea of UniDG is to finetune models during the inference stage, which saves the cost of iterative training. Specifically, we encourage models to learn the distribution of test data in an unsupervised manner and impose a penalty regarding the updating step of model parameters. The penalty term can effectively reduce the catastrophic forgetting issue as we would like to maximally preserve the valuable knowledge in the original model. Empirically, across 12 visual backbones, including CNN-, MLP-, and Transformer-based models, ranging from 1.89M to 303M parameters, UniDG shows an average accuracy improvement of +5.4% on DomainBed. These performance results demonstrate the superiority and versatility of UniDG. The code is publicly available at https://github.com/invictus717/UniDG
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Domain Generalization | DomainNet | UniDG + CORAL + ConvNeXt-B | Average Accuracy | 59.5 | #14 of 38 | Archive leaderboard | report |
| Domain Generalization | Office-Home | UniDG + CORAL + ConvNeXt-B | Average Accuracy | 88.9 | #3 of 45 | Archive leaderboard | report |
| Domain Generalization | PACS | UniDG + CORAL + ConvNeXt-B | Average Accuracy | 95.6 | #14 of 133 | Archive leaderboard | report |
| Domain Generalization | TerraIncognita | UniDG + CORAL + ConvNeXt-B | Average Accuracy | 69.6 | #1 of 30 | Archive leaderboard | report |
| Domain Generalization | VLCS | UniDG + CORAL + ConvNeXt-B | Average Accuracy | 84.5 | #2 of 37 | 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.
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