English

Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning

Computer Vision and Pattern Recognition 2026-05-12 v1

Abstract

Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge. However, in real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may later need to operate in rural or highway environments with different traffic patterns and weather conditions. This requires the model not only to overcome catastrophic forgetting, but also to effectively handle domain shifts. In this paper, we propose CrOss-sample Relational Fusion (CORF), a unified framework to address domain shift and catastrophic forgetting simultaneously. To enhance generalizability, we perform selective refinement of training samples by leveraging spatial contribution maps to highlight semantically informative regions. Furthermore, we incorporate predictive confidence to adaptively weigh samples, thereby facilitating the learning of domain-agnostic representations. To alleviate forgetting, we propose a cascaded distillation framework that captures cross-sample relational dependencies across multiple feature hierarchies, enabling multi-grained knowledge transfer from previous tasks. CORF can be seamlessly integrated into existing CIL algorithms to enhance their generalizability, achieving competitive performance across various benchmark datasets. Code is available at https://github.com/LAMDA-CL/TMM26-CORF .

Keywords

Cite

@article{arxiv.2605.08839,
  title  = {Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning},
  author = {Zhen-Hao Xie and Yan Wang and Hao Sun and Han-Jia Ye and De-Chuan Zhan and Da-Wei Zhou},
  journal= {arXiv preprint arXiv:2605.08839},
  year   = {2026}
}

Comments

Accepted by IEEE Transactions on Multimedia (TMM 2026). Code is available at https://github.com/LAMDA-CL/TMM26-CORF

R2 v1 2026-07-01T12:59:46.921Z