动态LoRA专家与原型集成匹配用于类增量学习
Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning
浏览论文内容
中文总结 AI 辅助
提出DLEPEM框架，通过为每个增量任务分配LoRA专家并集成原型匹配，解决类增量学习中的干扰与对齐问题，在标准及少样本基准上表现强劲。
中文摘要 AI 辅助
类增量学习（CIL）旨在持续学习新类别而不遗忘先前获得的知识。基于预训练模型的参数高效微调可减少参数开销，但可能遭受累积干扰以及推理样本与专门模块之间的次优对齐问题。我们提出动态LoRA专家与原型集成匹配（DLEPEM），一种两阶段无重放框架。DLEPEM为每个增量任务分配一个任务特定的LoRA专家以减少跨任务干扰，然后结合冻结的预训练模型原型与任务自适应LoRA专家原型，以实现可靠的任务级判别。在标准CIL和少样本CIL基准上的实验表明，在所评估的协议下具有强劲性能。
英文摘要
Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols.
发表机构
- School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。
