SDR-CIR: Semantic Debias Retrieval Framework For Training-free Zero-shot Composed Image Retrieval
2026 · Yi Sun, Jinyu Xu, Qing Xie, et al.
Abstract
Composed Image Retrieval (CIR) aims to retrieve a target image from a query composed of a reference image and modification text. Recent training-free zero-shot methods often employ Multimodal Large Language Models (MLLMs) with Chain-of-Thought (CoT) to compose a target image description for retrieval. However, due to the fuzzy matching nature of ZS-CIR, the generated description is prone to semantic bias relative to the target image. We propose SDR-CIR, a training-free Semantic Debias Ranking method based on CoT reasoning. First, Selective CoT guides the MLLM to extract visual content relevant to the modification text during image understanding, thereby reducing visual noise at the source. We then introduce a Semantic Debias Ranking with two steps, Anchor and Debias, to mitigate semantic bias. In the Anchor step, we fuse reference image features with target description features to reinforce useful semantics and supplement omitted cues. In the Debias step, we explicitly model the visual
Authors
(none)
Tags
Stats
Related papers
- Mcot-re: Multi-faceted Chain-of-thought And Re-ranking For Training-free Zero-shot Composed Image Retrieval (2025)0.00
- Reason-before-retrieve: One-stage Reflective Chain-of-thoughts For Training-free Zero-shot Composed Image Retrieval (2024)10.03
- Cotmr: Chain-of-thought Multi-scale Reasoning For Training-free 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
- Multimodal Reasoning Agent For Zero-shot Composed Image Retrieval (2025)0.00
- G-MIXER: Geodesic Mixup-based Implicit Semantic Expansion And Explicit Semantic Re-ranking For Zero-shot Composed Image Retrieval (2026)0.78
- Isearle: Improving Textual Inversion For Zero-shot Composed Image Retrieval (2024)12.09
- Zero-shot Composed Image Retrieval With Textual Inversion (2023)19.84