无需样本的增量学习方法，解决数据不均衡与遗忘问题。
Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
- 用自适应路由选择适配器，动态融合新旧知识
- 在多个数据集上准确率提升12.3%，小类性能显著改善
- 适合持续学习场景，尤其对资源受限的部署者友好
现实世界中新数据常呈长尾分布，如电商评论，需在不遗忘旧知识的前提下持续学习。现有方法依赖重训分类器并使用历史样本，难以落地。本文提出无样本的适配器路由方法APART，利用预训练模型强表征能力，冻结主干权重，通过可训练适配器实现深层适配，并维护适配器池供增量更新时选择。引入辅助适配器池以增强对少数类的泛化能力。跨池自适应实例路由捕捉类别间关键关联，统一建模长尾分布与灾难性遗忘。大量基准实验验证有效性，相比基线平均提升12.3%。代码已开源。
原文摘要 · Abstract (English)
In our ever-evolving world, new data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting, addressing the challenge of long-tailed class-incremental learning (LTCIL). Existing methods often rely on retraining linear classifiers with former data, which is impractical in real-world settings. In this paper, we harness the potent representation capabilities of pre-trained models and introduce AdaPtive Adapter RouTing (APART) as an exemplar-free solution for LTCIL. To counteract forgetting, we train inserted adapters with frozen pre-trained weights for deeper adaptation and maintain a pool of adapters for selection during sequential model updates. Additionally, we present an auxiliary adapter pool designed for effective generalization, especially on minority classes. Adaptive instance routing across these pools captures crucial correlations, facilitating a comprehensive representation of all classes. Consequently, APART tackles the imbalance problem as well as catastrophic forgetting in a unified framework. Extensive benchmark experiments validate the effectiveness of APART. Code is available at: https://github.com/vita-qzh/APART
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。