English

Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization

Computer Vision and Pattern Recognition 2025-07-18 v1

Abstract

Domain generalization (DG) aims to learn a model from source domains and apply it to unseen target domains with out-of-distribution data. Owing to CLIP's strong ability to encode semantic concepts, it has attracted increasing interest in domain generalization. However, CLIP often struggles to focus on task-relevant regions across domains, i.e., domain-invariant regions, resulting in suboptimal performance on unseen target domains. To address this challenge, we propose an attention-refocusing scheme, called Simulate, Refocus and Ensemble (SRE), which learns to reduce the domain shift by aligning the attention maps in CLIP via attention refocusing. SRE first simulates domain shifts by performing augmentation on the source data to generate simulated target domains. SRE then learns to reduce the domain shifts by refocusing the attention in CLIP between the source and simulated target domains. Finally, SRE utilizes ensemble learning to enhance the ability to capture domain-invariant attention maps between the source data and the simulated target data. Extensive experimental results on several datasets demonstrate that SRE generally achieves better results than state-of-the-art methods. The code is available at: https://github.com/bitPrincy/SRE-DG.

Keywords

Cite

@article{arxiv.2507.12851,
  title  = {Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization},
  author = {Ziyi Wang and Zhi Gao and Jin Chen and Qingjie Zhao and Xinxiao Wu and Jiebo Luo},
  journal= {arXiv preprint arXiv:2507.12851},
  year   = {2025}
}

Comments

\c{opyright} 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

R2 v1 2026-07-01T04:05:34.773Z