AI RESEARCH
FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval
arXiv CS.LG
•
ArXi:2604.09114v1 Announce Type: cross Composed image retrieval (CIR) aims to retrieve a target image that depicts a reference image modified by a textual description. While recent vision-language models (VLMs) achieve promising CIR performance by embedding images and text into a shared space for retrieval, they often fail to reason about what to preserve and what to change. This limitation hinders interpretability and yields suboptimal results, particularly in fine-grained domains like fashion. In this paper, we.