DetailFusion: A Dual-branch Framework with Detail Enhancement for 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, Song, Lin, Gao, Jun, Li, Peng, Hu, Weiming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916754788188160
author Yang, Yuxin
Zhou, Yinan
Chen, Yuxin
Zhang, Ziqi
Ma, Zongyang
Yuan, Chunfeng
Li, Bing
Song, Lin
Gao, Jun
Li, Peng
Hu, Weiming
author_facet Yang, Yuxin
Zhou, Yinan
Chen, Yuxin
Zhang, Ziqi
Ma, Zongyang
Yuan, Chunfeng
Li, Bing
Song, Lin
Gao, Jun
Li, Peng
Hu, Weiming
contents Composed Image Retrieval (CIR) aims to retrieve target images from a gallery based on a reference image and modification text as a combined query. Recent approaches focus on balancing global information from two modalities and encode the query into a unified feature for retrieval. However, due to insufficient attention to fine-grained details, these coarse fusion methods often struggle with handling subtle visual alterations or intricate textual instructions. In this work, we propose DetailFusion, a novel dual-branch framework that effectively coordinates information across global and detailed granularities, thereby enabling detail-enhanced CIR. Our approach leverages atomic detail variation priors derived from an image editing dataset, supplemented by a detail-oriented optimization strategy to develop a Detail-oriented Inference Branch. Furthermore, we design an Adaptive Feature Compositor that dynamically fuses global and detailed features based on fine-grained information of each unique multimodal query. Extensive experiments and ablation analyses not only demonstrate that our method achieves state-of-the-art performance on both CIRR and FashionIQ datasets but also validate the effectiveness and cross-domain adaptability of detail enhancement for CIR.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17796
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval
Yang, Yuxin
Zhou, Yinan
Chen, Yuxin
Zhang, Ziqi
Ma, Zongyang
Yuan, Chunfeng
Li, Bing
Song, Lin
Gao, Jun
Li, Peng
Hu, Weiming
Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Composed Image Retrieval (CIR) aims to retrieve target images from a gallery based on a reference image and modification text as a combined query. Recent approaches focus on balancing global information from two modalities and encode the query into a unified feature for retrieval. However, due to insufficient attention to fine-grained details, these coarse fusion methods often struggle with handling subtle visual alterations or intricate textual instructions. In this work, we propose DetailFusion, a novel dual-branch framework that effectively coordinates information across global and detailed granularities, thereby enabling detail-enhanced CIR. Our approach leverages atomic detail variation priors derived from an image editing dataset, supplemented by a detail-oriented optimization strategy to develop a Detail-oriented Inference Branch. Furthermore, we design an Adaptive Feature Compositor that dynamically fuses global and detailed features based on fine-grained information of each unique multimodal query. Extensive experiments and ablation analyses not only demonstrate that our method achieves state-of-the-art performance on both CIRR and FashionIQ datasets but also validate the effectiveness and cross-domain adaptability of detail enhancement for CIR.
title DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2505.17796