Reason-before-retrieve: One-stage Reflective Chain-of-thoughts For Training-free Zero-shot Composed Image Retrieval

Abstract

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 aligni

Stats

• citations6
• S2 citations—
• github stars69
• HF likes0
• heat score10.03
• arxiv keytang2024reason

Related papers

• Cotmr: Chain-of-thought Multi-scale Reasoning For Training-free Zero-shot Composed Image Retrieval (2025)0.00
• Mcot-re: Multi-faceted Chain-of-thought And Re-ranking For Training-free Zero-shot Composed Image Retrieval (2025)0.00
• Multimodal Reasoning Agent For Zero-shot Composed Image Retrieval (2025)0.00
• From Mapping To Composing: A Two-stage Framework For Zero-shot Composed Image Retrieval (2025)0.00
• Cir-cot: Towards Interpretable Composed Image Retrieval Via End-to-end Chain-of-thought Reasoning (2025)0.00
• SDR-CIR: Semantic Debias Retrieval Framework For Training-free Zero-shot Composed Image Retrieval (2026)0.00
• Fine-grained Zero-shot Composed Image Retrieval With Complementary Visual-semantic Integration (2026)1.24
• SETR: A Two-stage Semantic-enhanced Framework For Zero-shot Composed Image Retrieval (2025)0.00