Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval

TL;DR

This paper introduces an interactive image retrieval system using CLIP and relevance feedback, which adapts to user preferences without training new models, competing with state-of-the-art metric learning methods.

Contribution

It revisits relevance feedback for CLIP-based retrieval, enabling preference adaptation without training, and demonstrates effectiveness across various user preference scenarios.

Findings

Competitive accuracy with state-of-the-art metric learning methods.

Effective adaptation to diverse user preferences.

Improved retrieval accuracy with relevance feedback.

Abstract

Many image retrieval studies use metric learning to train an image encoder. However, metric learning cannot handle differences in users' preferences, and requires data to train an image encoder. To overcome these limitations, we revisit relevance feedback, a classic technique for interactive retrieval systems, and propose an interactive CLIP-based image retrieval system with relevance feedback. Our retrieval system first executes the retrieval, collects each user's unique preferences through binary feedback, and returns images the user prefers. Even when users have various preferences, our retrieval system learns each user's preference through the feedback and adapts to the preference. Moreover, our retrieval system leverages CLIP's zero-shot transferability and achieves high accuracy without training. We empirically show that our retrieval system competes well with state-of-the-art metric learning in category-based image retrieval, despite not training image encoders specifically for each dataset. Furthermore, we set up two additional experimental settings where users have various preferences: one-label-based image retrieval and conditioned image retrieval. In both cases, our retrieval system effectively adapts to each user's preferences, resulting in improved accuracy compared to image retrieval without feedback. Overall, our work highlights the potential benefits of integrating CLIP with classic relevance feedback techniques to enhance image retrieval.