MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval

2026-08-25

AI Summary

本文提出MulVec方法，通过细粒度角色感知匹配解决无需训练的零样本组合图像检索问题，提高检索精度。

Abstract

Training-free zero-shot composed image retrieval finds a target image in a gallery from a reference image and a text edit without learning from task-specific image triplets. Existing methods typically describe the target as a whole and match this description with a global image representation. This global matching can mix different semantic cues and lose fine- grained details. We propose MULVEC, a role-aware method whose compiler produces a structured query record that is mapped to four retrieval roles: Global describes the full target, Desired states what should appear, Preserve states what should remain, and Forbidden states what should disappear. Frozen encoders map the query to one target description vector and role-specific probe vectors, while each candidate is represented by one global visual vector and a bank of local visual vectors. The retrieval roles then use this shared evidence for their respective purposes, and a fixed weighted sum of their scores ranks the entire gallery in a single retrieval pass. Across CIRCO, CIRR, and FashionIQ and three backbone scales, MULVEC improves CIRCO mAP@5 by up to 23.0% over the strongest compared method and gives the best CIRR and FashionIQ results in our comparison.

Problem

• Training-free zero-shot composed image retrieval
• global matching
• semantic cues
• fine-grained details

Innovation

• Fine-Grained Role-Aware Matching
• Training-Free Zero-Shot Composed Image Retrieval
• Structured Query Record
• Frozen Encoders
• Role-Specific Probe Vectors