Image Retrieval with Mixed Initiative and Multimodal Feedback

TL;DR

This paper introduces a mixed-initiative, multimodal feedback system for image retrieval that dynamically balances user and system control using reinforcement learning, leading to faster and more accurate search results.

Contribution

It presents a novel reinforcement learning framework enabling dynamic selection among sketching, attribute feedback, and question answering for improved image retrieval.

Findings

Outperforms three baseline methods on three datasets.

Enables faster retrieval through optimized interaction choices.

Demonstrates effectiveness of mixed-initiative, multimodal feedback.

Abstract

How would you search for a unique, fashionable shoe that a friend wore and you want to buy, but you didn't take a picture? Existing approaches propose interactive image search as a promising venue. However, they either entrust the user with taking the initiative to provide informative feedback, or give all control to the system which determines informative questions to ask. Instead, we propose a mixed-initiative framework where both the user and system can be active participants, depending on whose initiative will be more beneficial for obtaining high-quality search results. We develop a reinforcement learning approach which dynamically decides which of three interaction opportunities to give to the user: drawing a sketch, providing free-form attribute feedback, or answering attribute-based questions. By allowing these three options, our system optimizes both the informativeness and exploration capabilities allowing faster image retrieval. We outperform three baselines on three datasets and extensive experimental settings.