Chatting Makes Perfect: Chat-based Image Retrieval

TL;DR

ChatIR introduces a chat-based image retrieval system that uses dialogue and large language models to improve search accuracy, achieving over 78% success in retrieving images from a large dataset after multiple dialogue rounds.

Contribution

This work presents ChatIR, a novel system that employs conversational dialogue and large language models for iterative image retrieval, significantly enhancing retrieval success over traditional single-query methods.

Findings

Achieves over 78% success rate in retrieving target images after 5 dialogue rounds.

Outperforms single shot text-to-image retrieval with 64% success.

Demonstrates the effectiveness of dialog-based retrieval over baseline models.

Abstract

Chats emerge as an effective user-friendly approach for information retrieval, and are successfully employed in many domains, such as customer service, healthcare, and finance. However, existing image retrieval approaches typically address the case of a single query-to-image round, and the use of chats for image retrieval has been mostly overlooked. In this work, we introduce ChatIR: a chat-based image retrieval system that engages in a conversation with the user to elicit information, in addition to an initial query, in order to clarify the user's search intent. Motivated by the capabilities of today's foundation models, we leverage Large Language Models to generate follow-up questions to an initial image description. These questions form a dialog with the user in order to retrieve the desired image from a large corpus. In this study, we explore the capabilities of such a system tested on a large dataset and reveal that engaging in a dialog yields significant gains in image retrieval. We start by building an evaluation pipeline from an existing manually generated dataset and explore different modules and training strategies for ChatIR. Our comparison includes strong baselines derived from related applications trained with Reinforcement Learning. Our system is capable of retrieving the target image from a pool of 50K images with over 78% success rate after 5 dialogue rounds, compared to 75% when questions are asked by humans, and 64% for a single shot text-to-image retrieval. Extensive evaluations reveal the strong capabilities and examine the limitations of CharIR under different settings. Project repository is available at https://github.com/levymsn/ChatIR.