Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user intent more precisely. Existing training-free zero-shot CIR (ZS-CIR) methods often employ a two-stage process: they first generate a caption for the reference image and then use Large Language Models for reasoning to obtain a target description. However, these methods suffer from missing critical visual details and limited reasoning capabilities, leading to suboptimal retrieval performance. To address these challenges, we propose a novel, training-free one-stage method, One-Stage Reflective Chain-of-Thought Reasoning for ZS-CIR (OSrCIR), which employs Multimodal Large Language Models to retain essential visual information in a single-stage reasoning process, eliminating the information loss seen in two-stage methods. Our Reflective Chain-of-Thought framework further improves interpretative accuracy by aligning manipulation intent with contextual cues from reference images. OSrCIR achieves performance gains of 1.80% to 6.44% over existing training-free methods across multiple tasks, setting new state-of-the-art results in ZS-CIR and enhancing its utility in vision-language applications. Our code will be available at https://github.com/Pter61/osrcir2024/.
@article{arxiv.2412.11077,
title = {Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval},
author = {Yuanmin Tang and Xiaoting Qin and Jue Zhang and Jing Yu and Gaopeng Gou and Gang Xiong and Qingwei Ling and Saravan Rajmohan and Dongmei Zhang and Qi Wu},
journal= {arXiv preprint arXiv:2412.11077},
year = {2024}
}