Preprint
Jul 2026
Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval
This paper introduces a Vision-Free CIR framework that addresses this challenge through two key techniques: Attribute-Augmented Hybrid Scoring, which compensates for lost visual details via explicit attribute matching, and LLM-Based Reranking, which verifies semantic consistency of top candidates.
Ryotaro Shimada, Yu-Chieh Lin, Yuji Nozawa et al.
· 1 citation