发表机构
National Key Laboratory of Radar Signal Processing, Xidian University; The University of Hong Kong; Institute of Artificial Intelligence (TeleAI) of China Telecom（西安电子科技大学雷达信号处理国家重点实验室; 香港大学; 中国电信人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于预训练模型的类增量学习问题，提出Miles方法，通过解耦可学习模块与预训练模型，利用骨干网络中间特征先验信息实现参数空间高效扩展，经实验验证在多种CIL设置中性能领先。
AI 中文摘要
类增量学习（CIL）旨在从数据流中持续学习新概念而不遗忘。与需从头学习模型的典型CIL方法不同，预训练模型（PTM）通过微调能轻松适应新任务。但现有基于PTM的CIL方法在性能和计算开销间难以权衡。为此提出Miles，利用预训练知识中的先验信息，通过引导优化实现参数空间的高效扩展。具体通过解耦可学习模块与预训练模型，利用骨干网络中间特征的先验信息灵活扩展参数。采用中心损失引导新类别在新任务子空间中向对应原型聚类，引入辅助距离正则项保持跨任务的度量平衡。在六个基准数据集上的大量实验表明，Miles在各种CIL设置中取得了领先性能。
英文摘要
Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning. However, existing PTM-based CIL methods fail to achieve a trade-off between performance and computational expenditure, i.e., they either adopt the same parameter space so that leading catastrophic forgetting, or expand a new branch for each task but adding more computational cost. To this end, we propose MetrIc Learning with Expandable Subspace (Miles) to harness the prior information within pre-trained knowledge, thereby orchestrating an efficient expansion of the parameter space through guided optimization. Specifically, it decouples the learnable modules with the pre-trained model, exploiting prior information from intermediate features of the backbone network to enable more flexible parameter expansion. Then, a central loss is adopted to guide the new category to cluster towards the corresponding prototype in the new task subspace while incorporating an auxiliary distance regularization term to maintain metric equilibrium across tasks. Extensive experiments on six benchmark datasets demonstrate that Miles achieves state-of-the-art performance in various CIL settings.
CommentsThis work has been accepted by IEEE Transactions on Image Processing
Journal refIEEE Transactions on Image Processing, early access, 2026
