统一解决模型遗忘与跨域适应问题，提升增量学习泛化能力。
Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning
- 通过空间贡献图筛选关键区域，自适应加权样本增强泛化性。
- 多层级关系蒸馏机制缓解遗忘，实现跨任务知识迁移。
- 可无缝集成现有方法，适合实际场景中持续学习的系统部署。
类增量学习（CIL）要求系统在学习新类别时保留旧知识。但在自动驾驶等真实场景中，模型需从晴天城市道路迁移到乡村或高速路，面临交通模式和天气变化带来的领域偏移。本文提出跨样本关系融合框架CORF，同时应对灾难性遗忘与领域漂移。通过空间贡献图识别语义重要区域，结合预测置信度自适应加权样本，促进领域无关表示学习。设计级联蒸馏结构，捕捉多层级特征间的跨样本关系，实现多粒度知识传递。CORF可无缝嵌入现有CIL算法，显著提升在多个基准数据集上的表现。代码已开源：https://github.com/LAMDA-CL/TMM26-CORF。
原文摘要 · Abstract (English)
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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。