Papers › Test-time Training for Data-efficient UCDR

Test-time Training for Data-efficient UCDR

19 Aug 2022arXiv:2208.09198archive 2025-07-28

Soumava Paul, Titir Dutta, Aheli Saha, Abhishek Samanta, Soma Biswas

Image retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer in this direction. A common practice in any such generalized classification or retrieval algorithm is to exploit samples from many domains during training to learn a domain-invariant representation of data. Such criterion is often restrictive, and thus in this work, for the first time, we explore the generalized retrieval problem in a data-efficient manner. Specifically, we aim to generalize any pre-trained cross-domain retrieval network towards any unknown query domain/category, by means of adapting the model on the test data leveraging self-supervised learning techniques. Toward that goal, we explored different self-supervised loss functions~(for example, RotNet, JigSaw, Barlow Twins, etc.) and analyze their effectiveness for the same. Extensive experiments demonstrate the proposed approach is simple, easy to implement, and effective in handling data-efficient UCDR.

PaperPDFCode

Code

mvp18/ttt-ucdr officialmentioned in papermentioned 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 AdaptationImage ClassificationImage RetrievalRetrievalSelf-Supervised LearningSemantic SegmentationSketch-Based Image Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Barlow TwinsJigsawRotNetTest

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