面向边缘持续学习的关键图像块感知稀疏提示与解耦训练
Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
把「关键图像块采样」作为任务感知的词元削减手段，配合提示词与分类器解耦训练来降低反向传播开销，为在显存受限的边缘设备上做视觉模型的持续适配提供了可复用的训练期效率方案。
原文依据 critical patch sampling (CPS) for task-aware token reduction and decoupled prompt and classifier training (DPCT)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论边缘设备上的持续学习（CL）不仅需要高准确率，还需要训练期效率，以在严格的内存与计算约束下支持设备端自适应。基于提示词的持续学习（PCL）虽参数高效且准确率具有竞争力，但已有工作主要关注准确率或推理期性能，往往忽视了设备端训练的内存与计算开销。本文提出 CPS-Prompt，一个关键图像块感知的稀疏提示框架，通过集成关键图像块采样（CPS）实现任务感知的词元削减，并采用提示词与分类器解耦训练（DPCT）降低反向传播开销，从而显式针对训练期内存占用与计算成本。在三个公开基准和真实边缘硬件上的实验表明，CPS-Prompt 相比均衡配置的 CODA-Prompt 基线在峰值内存、训练时间和能效上提升约 1.6 倍，同时平均准确率与最优的 C-Prompt 相差保持在 2% 以内，并与 CODA-Prompt 的准确率保持竞争力。代码见 https://github.com/laymond1/cpsprompt。
英文原文摘要 1162 字符
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/cpsprompt.