Revisiting Relevance Feedback For Clip-based Interactive Image Retrieval

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

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keynara2024revisiting

Related papers

• An Improved Relevance Feedback In CBIR (2020)0.00
• Dialog-based Interactive Image Retrieval (2018)0.00
• Image Retrieval With A Bayesian Model Of Relevance Feedback (2016)0.00
• Advancing Image Retrieval With Few-shot Learning And Relevance Feedback (2023)0.00
• Advancements In Content-based Image Retrieval: A Comprehensive Survey Of Relevance Feedback Techniques (2023)0.00
• Image Retrieval With Mixed Initiative And Multimodal Feedback (2018)8.09
• Robust Relevance Feedback For Interactive Known-item Video Search (2025)0.00
• Optimizing CLIP Models For Image Retrieval With Maintained Joint-embedding Alignment (2024)6.34