Test-time Training For Data-efficient UCDR

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypaul2022test

Related papers

• Semantic Feature Learning For Universal Unsupervised Cross-domain Retrieval (2024)0.00
• DUDE: Diffusion-based Unsupervised Cross-domain Image Retrieval (2025)0.00
• Universal Cross-domain Retrieval: Generalizing Across Classes And Domains (2021)8.09
• Ucdr-adapter: Exploring Adaptation Of Pre-trained Vision-language Models For Universal Cross-domain Retrieval (2024)4.52
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• Syncdr : Training Cross Domain Retrieval Models With Synthetic Data (2023)0.00
• Pros: Prompting-to-simulate Generalized Knowledge For Universal Cross-domain Retrieval (2023)12.56
• Unsupervised Cross-domain Image Retrieval Via Prototypical Optimal Transport (2024)8.09