面向边缘设备的持续学习中关键补丁感知稀疏提示方法
Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
AI总结：
本文提出CPS-Prompt方法，通过关键补丁采样和解耦训练降低边缘设备上的训练内存和计算成本，实验证明其在内存、训练时间和能效方面优于基线模型，同时保持与现有方法相当的精度。
摘要：
边缘设备上的持续学习需要高精度和高效的训练时间，以支持设备上的适应。尽管基于提示的持续学习（PCL）参数高效且准确，但先前工作主要关注精度或推理时间性能，忽略了设备训练的内存和计算成本。本文提出CPS-Prompt，一种关键补丁感知的稀疏提示框架，通过整合关键补丁采样（CPS）进行任务感知的token减少和解耦提示和分类器训练（DPCT）来减少反向传播开销。实验表明，CPS-Prompt在三个公开基准和真实边缘硬件上比平衡的CODA-Prompt基线提高了约1.6倍的峰值内存、训练时间和能效，同时在平均精度上保持与最先进的C-Prompt相当，并在精度上与CODA-Prompt竞争。代码可在https://github.com/laymond1/cps-prompt上获得。
英文摘要：
Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is parameter-efficient and achieves competitive accuracy, prior work has focused mainly on accuracy or inference-time performance, often overlooking the memory and computational costs of on-device training. In this paper, we propose CPS-Prompt, a critical patch-aware sparse prompting framework that explicitly targets training-time memory usage and computational cost by integrating critical patch sampling (CPS) for task-aware token reduction and decoupled prompt and classifier training (DPCT) to reduce backpropagation overhead. Experiments on three public benchmarks and real edge hardware show that CPS-Prompt improves peak memory, training time, and energy efficiency by about 1.6x over the balanced CODA-Prompt baseline, while maintaining accuracy within 2% of the state-of-the-art C-Prompt on average and remaining competitive with CODA-Prompt in accuracy. The code is available at https://github.com/laymond1/cps-prompt.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
