Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Yuxin, Zhou, Yinan, Chen, Yuxin, Zhang, Ziqi, Ma, Zongyang, Yuan, Chunfeng, Li, Bing, Gao, Jun, Hu, Weiming
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866910107507359744
author	Yang, Yuxin Zhou, Yinan Chen, Yuxin Zhang, Ziqi Ma, Zongyang Yuan, Chunfeng Li, Bing Gao, Jun Hu, Weiming
author_facet	Yang, Yuxin Zhou, Yinan Chen, Yuxin Zhang, Ziqi Ma, Zongyang Yuan, Chunfeng Li, Bing Gao, Jun Hu, Weiming
contents	Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inherently prioritizes semantic matching, struggling to reliably retrieve a user-specified instance across contexts. In practice, emphasizing concrete instance fidelity over broad semantics is often more consequential. In this work, we propose Object-Anchored Composed Image Retrieval (OACIR), a novel fine-grained retrieval task that mandates strict instance-level consistency. To advance research on this task, we construct OACIRR (OACIR on Real-world images), the first large-scale, multi-domain benchmark comprising over 160K quadruples and four challenging candidate galleries enriched with hard-negative instance distractors. Each quadruple augments the compositional query with a bounding box that visually anchors the object in the reference image, providing a precise and flexible way to ensure instance preservation. To address the OACIR task, we propose AdaFocal, a framework featuring a Context-Aware Attention Modulator that adaptively intensifies attention within the specified instance region, dynamically balancing focus between the anchored instance and the broader compositional context. Extensive experiments demonstrate that AdaFocal substantially outperforms existing compositional retrieval models, particularly in maintaining instance-level fidelity, thereby establishing a robust baseline for this challenging task while opening new directions for more flexible, instance-aware retrieval systems.
format	Preprint
id	arxiv_https___arxiv_org_abs_2604_05393
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval Yang, Yuxin Zhou, Yinan Chen, Yuxin Zhang, Ziqi Ma, Zongyang Yuan, Chunfeng Li, Bing Gao, Jun Hu, Weiming Computer Vision and Pattern Recognition Multimedia Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inherently prioritizes semantic matching, struggling to reliably retrieve a user-specified instance across contexts. In practice, emphasizing concrete instance fidelity over broad semantics is often more consequential. In this work, we propose Object-Anchored Composed Image Retrieval (OACIR), a novel fine-grained retrieval task that mandates strict instance-level consistency. To advance research on this task, we construct OACIRR (OACIR on Real-world images), the first large-scale, multi-domain benchmark comprising over 160K quadruples and four challenging candidate galleries enriched with hard-negative instance distractors. Each quadruple augments the compositional query with a bounding box that visually anchors the object in the reference image, providing a precise and flexible way to ensure instance preservation. To address the OACIR task, we propose AdaFocal, a framework featuring a Context-Aware Attention Modulator that adaptively intensifies attention within the specified instance region, dynamically balancing focus between the anchored instance and the broader compositional context. Extensive experiments demonstrate that AdaFocal substantially outperforms existing compositional retrieval models, particularly in maintaining instance-level fidelity, thereby establishing a robust baseline for this challenging task while opening new directions for more flexible, instance-aware retrieval systems.
title	Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval
topic	Computer Vision and Pattern Recognition Multimedia
url	https://arxiv.org/abs/2604.05393