SOURCE-LINKED INTELLIGENCE

AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Composed image retrieval (CIR) retrieves a target image from a reference image and a text modification. This paper studies metadata-available CIR reranking, where a fixed CIR model first returns a candidate pool and gallery metadata is then used for second-stage concept-guided scoring. We introduce AutoConcept, a training-free reranker that converts concept evidence into an interpretable memory. AutoConcept filters noisy concepts, activates query-relevant positive constraints with an auxiliary negative penalty, and combines base retrieval scores with metadata-based concept-candidate alignment

Read original source ↗ Open in workspace

recordType

paper

region

Global