Papers › Combining inherent knowledge of vision-language models with unsupervised domain...

Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance

7 Dec 2023arXiv:2312.04066archive 2025-07-28

Thomas Westfechtel, Dexuan Zhang, Tatsuya Harada

Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset and transferring its knowledge to a similar but different target dataset. Meanwhile, current vision-language models exhibit remarkable zero-shot prediction capabilities. In this work, we combine knowledge gained through UDA with the inherent knowledge of vision-language models. We introduce a strong-weak guidance learning scheme that employs zero-shot predictions to help align the source and target dataset. For the strong guidance, we expand the source dataset with the most confident samples of the target dataset. Additionally, we employ a knowledge distillation loss as weak guidance. The strong guidance uses hard labels but is only applied to the most confident predictions from the target dataset. Conversely, the weak guidance is employed to the whole dataset but uses soft labels. The weak guidance is implemented as a knowledge distillation loss with (shifted) zero-shot predictions. We show that our method complements and benefits from prompt adaptation techniques for vision-language models. We conduct experiments and ablation studies on three benchmarks (OfficeHome, VisDA, and DomainNet), outperforming state-of-the-art methods. Our ablation studies further demonstrate the contributions of different components of our algorithm.

PaperPDFCode

Code

ThomasWestfechtel/SWG 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 AdaptationKnowledge DistillationLanguage ModellingSelf-Knowledge DistillationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation DomainNet SWG Accuracy 66.1 #3 of 4 Archive leaderboard report
Domain Adaptation Office-Home SWG Accuracy 92.3 #1 of 29 Archive leaderboard report
Domain Adaptation VisDA2017 SWG Accuracy 92.7 #4 of 28 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

ALIGNKnowledge Distillation

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