PF-UCDR: A Local-Aware RGB-Phase Fusion Network with Adaptive Prompts for Universal Cross-Domain Retrieval
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Universal Cross-Domain Retrieval (UCDR) aims to match semantically related images across domains and categories not seen during training. While vision-language pre-trained models offer strong global alignment, we are inspired by the observation that local structures, such as shapes, contours, and textures, often remain stable across domains, and thus propose to model them explicitly at the patch level. We present PF-UCDR, a framework built upon frozen vision-language backbones that performs patch-wise fusion of RGB and phase representations. Central to our design is a Fusing Vision Encoder, which applies masked cross-attention to spatially aligned RGB and phase patches, enabling fine-grained integration of complementary appearance and structural cues. Additionally, we incorporate adaptive visual prompts that condition image encoding based on domain and class context. Local and global fusion modules aggregate these enriched features, and a two-stage training strategy progressively optimizes alignment and retrieval objectives. Experiments on standard UCDR benchmarks demonstrate that PF-UCDR significantly outperforms existing methods, validating the effectiveness of structure-aware local fusion grounded in multimodal pretraining. Our code is publicly available at https://github.com/djzgroup/PF-UCDR.
Description
CCS Concepts: Computing methodologies → Computer vision tasks; Visual content-based indexing and retrieval; Image representations
@inproceedings{10.2312:pg.20251279,
booktitle = {Pacific Graphics Conference Papers, Posters, and Demos},
editor = {Christie, Marc and Han, Ping-Hsuan and Lin, Shih-Syun and Pietroni, Nico and Schneider, Teseo and Tsai, Hsin-Ruey and Wang, Yu-Shuen and Zhang, Eugene},
title = {{PF-UCDR: A Local-Aware RGB-Phase Fusion Network with Adaptive Prompts for Universal Cross-Domain Retrieval}},
author = {Wu, Yiqi and Hu, Ronglei and Wu, Huachao and He, Fazhi and Zhang, Dejun},
year = {2025},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {10.2312/pg.20251279}
}