为微型无人机群设计低功耗联邦持续学习方案，提升隐私保护下的识别准确率。
On-Device Federated Continual Learning on RISC-V-based Ultra-Low-Power SoC for Intelligent Nano-Drone Swarms
- 基于正则化方法，在多无人机上实现边端持续学习。
- 相比直接微调，识别准确率提升24%，单轮本地训练仅需178毫秒。
- 适用于资源受限的电池供电边缘设备，适合智能无人机集群应用。
基于RISC-V的架构正在推动智能边缘设备中的高效边端学习（ODL）。当应用于多个节点时，ODL可构建保护数据隐私的智能传感网络。然而，开发具备ODL能力且电池供电的嵌入式平台面临巨大挑战，包括计算资源受限和设备寿命短，以及灾难性遗忘等固有学习问题。为此，我们提出一种针对多个微型无人机执行人脸识别任务的正则化方法驱动的边端联邦持续学习算法。我们在一个基于RISC-V的10核超低功耗SoC上验证了该方法，优化了ODL的计算需求。实验表明，相较于直接微调，分类准确率提升24%，单次本地周期耗时178毫秒，全局周期耗时10.5秒，证明了该架构在此任务上的有效性。
原文摘要 · Abstract (English)
RISC-V-based architectures are paving the way for efficient On-Device Learning (ODL) in smart edge devices. When applied across multiple nodes, ODL enables the creation of intelligent sensor networks that preserve data privacy. However, developing ODL-capable, battery-operated embedded platforms presents significant challenges due to constrained computational resources and limited device lifetime, besides intrinsic learning issues such as catastrophic forgetting. We face these challenges by proposing a regularization-based On-Device Federated Continual Learning algorithm tailored for multiple nano-drones performing face recognition tasks. We demonstrate our approach on a RISC-V-based 10-core ultra-low-power SoC, optimizing the ODL computational requirements. We improve the classification accuracy by 24% over naive fine-tuning, requiring 178 ms per local epoch and 10.5 s per global epoch, demonstrating the effectiveness of the architecture for this task.
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。