Vision-Free Composed Image Retrieval Sets New Zero-Shot Benchmark with Attribute-Augmented Scoring and LLM Reranking

Jul 15, 2026

A new framework for Composed Image Retrieval (CIR) achieves state-of-the-art zero-shot performance on the CIRR dataset (44.04% R@1, an improvement of 8.79%) without using visual features. The approach combines attribute-augmented hybrid scoring to address the loss of visual detail and LLM-based reranking to ensure semantic consistency. Ablation studies confirm that both components contribute to the performance gains.

Why it matters: This work shows that vision-free methods can outperform traditional approaches on complex multimodal retrieval tasks, suggesting new directions for efficient and simplified retrieval systems.

Full story at: arXiv Information Retrieval ↗