English

Causality-based Dual-Contrastive Learning Framework for Domain Generalization

Computer Vision and Pattern Recognition 2023-03-23 v2

Abstract

Domain Generalization (DG) is essentially a sub-branch of out-of-distribution generalization, which trains models from multiple source domains and generalizes to unseen target domains. Recently, some domain generalization algorithms have emerged, but most of them were designed with non-transferable complex architecture. Additionally, contrastive learning has become a promising solution for simplicity and efficiency in DG. However, existing contrastive learning neglected domain shifts that caused severe model confusions. In this paper, we propose a Dual-Contrastive Learning (DCL) module on feature and prototype contrast. Moreover, we design a novel Causal Fusion Attention (CFA) module to fuse diverse views of a single image to attain prototype. Furthermore, we introduce a Similarity-based Hard-pair Mining (SHM) strategy to leverage information on diversity shift. Extensive experiments show that our method outperforms state-of-the-art algorithms on three DG datasets. The proposed algorithm can also serve as a plug-and-play module without usage of domain labels.

Keywords

Cite

@article{arxiv.2301.09120,
  title  = {Causality-based Dual-Contrastive Learning Framework for Domain Generalization},
  author = {Zining Chen and Weiqiu Wang and Zhicheng Zhao and Aidong Men},
  journal= {arXiv preprint arXiv:2301.09120},
  year   = {2023}
}

Comments

Inadequate proof of the effectiveness of the method

R2 v1 2026-06-28T08:17:18.256Z