DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval

• URL: http://arxiv.org/abs/2505.17796v1
• Date: Fri, 23 May 2025 12:15:23 GMT
• Title: DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval
• Authors: Yuxin Yang, Yinan Zhou, Yuxin Chen, Ziqi Zhang, Zongyang Ma, Chunfeng Yuan, Bing Li, Lin Song, Jun Gao, Peng Li, Weiming Hu,
• Abstract summary: Composed Image Retrieval (CIR) aims to retrieve target images from a gallery based on a reference image and modification text as a combined query.<n>Recent approaches focus on balancing global information from two modalities and encode the query into a unified feature for retrieval.<n>We propose DetailFusion, a novel dual-branch framework that effectively coordinates information across global and detailed granularities.
• Score: 51.30915462824879
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model [24.774935133996074]
  We propose a two-stage refinement framework that fully integrates images and prompts by using a lightweight refiner.<n>Our SAM-REF model outperforms the current state-of-the-art method in most metrics on segmentation quality without compromising efficiency.
  arXiv  Detail & Related papers  (2024-08-21T11:18:35Z)
• Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification [60.20318058777603]
  Generalizable vehicle re-identification (ReID) seeks to develop models that can adapt to unknown target domains without the need for fine-tuning or retraining.<n>Previous works have mainly focused on extracting domain-invariant features by aligning data distributions between source domains.<n>We propose a two-stage Multi-expert Knowledge Confrontation and Collaboration (MiKeCoCo) method to solve this unique problem.
  arXiv  Detail & Related papers  (2024-07-10T04:06:39Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• CoSeR: Bridging Image and Language for Cognitive Super-Resolution [74.24752388179992]
  We introduce the Cognitive Super-Resolution (CoSeR) framework, empowering SR models with the capacity to comprehend low-resolution images. We achieve this by marrying image appearance and language understanding to generate a cognitive embedding. To further improve image fidelity, we propose a novel condition injection scheme called "All-in-Attention"
  arXiv  Detail & Related papers  (2023-11-27T16:33:29Z)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction [13.454953507205278]
  Multi-Modal Relation Extraction aims at identifying the relation between two entities in texts that contain visual clues. We propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects. Our approach achieves excellent performance compared to strong competitors, even in the few-shot situation.
  arXiv  Detail & Related papers  (2023-06-19T15:31:34Z)
• HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval [13.061063817876336]
  We propose a novel Hierarchical Graph Alignment Network (HGAN) for image-text retrieval. First, to capture the comprehensive multimodal features, we construct the feature graphs for the image and text modality respectively. Then, a multi-granularity shared space is established with a designed Multi-granularity Feature Aggregation and Rearrangement (MFAR) module. Finally, the ultimate image and text features are further refined through three-level similarity functions to achieve the hierarchical alignment.
  arXiv  Detail & Related papers  (2022-12-16T05:08:52Z)
• Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information [15.32353270625554]
  Cross-modal remote sensing text-image retrieval (RSCTIR) has recently become an urgent research hotspot due to its ability of enabling fast and flexible information extraction on remote sensing (RS) images. We first propose a novel RSCTIR framework based on global and local information (GaLR), and design a multi-level information dynamic fusion (MIDF) module to efficaciously integrate features of different levels. Experiments on public datasets strongly demonstrate the state-of-the-art performance of GaLR methods on the RSCTIR task.
  arXiv  Detail & Related papers  (2022-04-21T03:18:09Z)
• Dense Dual-Attention Network for Light Field Image Super-Resolution [13.683743266136014]
  Light field (LF) images can be used to improve the performance of image super-resolution (SR) It is challenging to incorporate distinctive information from different views for LF image SR. We propose a dense dual-attention network for LF image SR.
  arXiv  Detail & Related papers  (2021-10-23T02:10:47Z)
• Deep Burst Super-Resolution [165.90445859851448]
  We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
  arXiv  Detail & Related papers  (2021-01-26T18:57:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.