Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models

TL;DR

This paper introduces an interactive image retrieval system that leverages large language models and vision-language models to iteratively refine queries, significantly improving recall and addressing semantic gaps in traditional methods.

Contribution

The paper presents a novel multi-turn interactive image retrieval system integrating LLM-based query denoising and VLM-based captioning, along with a new dataset for evaluation.

Findings

Achieved a 10% improvement in recall over baseline methods.

Validated the effectiveness of query refinement through experiments.

Demonstrated state-of-the-art performance in image retrieval tasks.

Abstract

Image search stands as a pivotal task in multimedia and computer vision, finding applications across diverse domains, ranging from internet search to medical diagnostics. Conventional image search systems operate by accepting textual or visual queries, retrieving the top-relevant candidate results from the database. However, prevalent methods often rely on single-turn procedures, introducing potential inaccuracies and limited recall. These methods also face the challenges, such as vocabulary mismatch and the semantic gap, constraining their overall effectiveness. To address these issues, we propose an interactive image retrieval system capable of refining queries based on user relevance feedback in a multi-turn setting. This system incorporates a vision language model (VLM) based image captioner to enhance the quality of text-based queries, resulting in more informative queries with each iteration. Moreover, we introduce a large language model (LLM) based denoiser to refine text-based query expansions, mitigating inaccuracies in image descriptions generated by captioning models. To evaluate our system, we curate a new dataset by adapting the MSR-VTT video retrieval dataset to the image retrieval task, offering multiple relevant ground truth images for each query. Through comprehensive experiments, we validate the effectiveness of our proposed system against baseline methods, achieving state-of-the-art performance with a notable 10\% improvement in terms of recall. Our contributions encompass the development of an innovative interactive image retrieval system, the integration of an LLM-based denoiser, the curation of a meticulously designed evaluation dataset, and thorough experimental validation.