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

2026-09-01

AI Summary

本文提出AutoConcept，一种无需训练的概念引导重排序方法，用于元数据可用的组合图像检索，通过过滤噪声概念、激活相关正约束及结合基础检索分数与元数据对齐来提高检索精度。

Abstract

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 through inference-time calibration. On FashionIQ, AutoConcept yields significant early-rank improvements over WeiMoCIR and consistent plug-in gains on LinCIR candidate pools. Metadata-aware controls show that structured concept memory adds signal beyond direct query-text and extracted-attribute matching, while a query-only variant further supports the effectiveness of concept-level reranking. A supplementary real-human concept-label study indicates that the same memory interface can consume participant-provided evidence. These results position AutoConcept as an interpretable concept-memory reranker for product-style CIR galleries with available metadata.

Problem

• Composed Image Retrieval
• Reranking
• Metadata
• Concept-Guided

Innovation

• Training-Free Reranking
• Concept-Guided Scoring
• Metadata-Aware Controls
• Inference-Time Calibration
• Interpretable Memory