Dialog-based Interactive Image Retrieval

TL;DR

This paper presents a novel dialog-based interactive image retrieval system that uses natural language feedback and reinforcement learning to improve retrieval accuracy and user experience.

Contribution

It introduces a reinforcement learning framework for dialog-based image retrieval using natural language feedback, trained with a user simulator, and demonstrates superior performance in footwear retrieval.

Findings

Better retrieval accuracy than baseline methods

Natural language feedback enhances communication and effectiveness

Effective in both simulated and real-world data

Abstract

Existing methods for interactive image retrieval have demonstrated the merit of integrating user feedback, improving retrieval results. However, most current systems rely on restricted forms of user feedback, such as binary relevance responses, or feedback based on a fixed set of relative attributes, which limits their impact. In this paper, we introduce a new approach to interactive image search that enables users to provide feedback via natural language, allowing for more natural and effective interaction. We formulate the task of dialog-based interactive image retrieval as a reinforcement learning problem, and reward the dialog system for improving the rank of the target image during each dialog turn. To mitigate the cumbersome and costly process of collecting human-machine conversations as the dialog system learns, we train our system with a user simulator, which is itself trained to describe the differences between target and candidate images. The efficacy of our approach is demonstrated in a footwear retrieval application. Experiments on both simulated and real-world data show that 1) our proposed learning framework achieves better accuracy than other supervised and reinforcement learning baselines and 2) user feedback based on natural language rather than pre-specified attributes leads to more effective retrieval results, and a more natural and expressive communication interface.