在边缘设备上直接训练高效鲁棒的神经网络，无需云端参与。
Growing Efficient Accurate and Robust Neural Networks on the Edge
- 从低复杂度网络开始，通过一次增长策略动态扩展模型
- 在Jetson Xavier NX上实现高准确率与对常见畸变的强鲁棒性
- 适合资源受限场景下隐私敏感的本地模型部署
深度学习系统在资源受限的边缘设备上广泛部署受到高计算复杂度和对分布外数据（尤其是自然常见的数据畸变）脆弱性的制约。现有方案依赖云端训练并压缩模型后再部署，导致本地数据上传带来高能耗和延迟，并引发隐私担忧。本文提出GEARnn（Growing Efficient, Accurate, and Robust neural networks），实现完全在边缘设备上原位生长与训练鲁棒网络。从低复杂度初始骨干网络出发，利用一次性增长（OSG）策略在满足边缘设备内存限制的前提下扩展网络结构，再通过高效鲁棒增强（ERA）提升模型鲁棒性，获得最终网络。我们在NVIDIA Jetson Xavier NX上验证了该方法，分析了准确性、鲁棒性、模型大小、能耗与训练时间之间的权衡。结果表明，可在边缘设备上构建高效、准确且鲁棒的神经网络。
原文摘要 · Abstract (English)
The ubiquitous deployment of deep learning systems on resource-constrained Edge devices is hindered by their high computational complexity coupled with their fragility to out-of-distribution (OOD) data, especially to naturally occurring common corruptions. Current solutions rely on the Cloud to train and compress models before deploying to the Edge. This incurs high energy and latency costs in transmitting locally acquired field data to the Cloud while also raising privacy concerns. We propose GEARnn (Growing Efficient, Accurate, and Robust neural networks) to grow and train robust networks in-situ, i.e., completely on the Edge device. Starting with a low-complexity initial backbone network, GEARnn employs One-Shot Growth (OSG) to grow a network satisfying the memory constraints of the Edge device using clean data, and robustifies the network using Efficient Robust Augmentation (ERA) to obtain the final network. We demonstrate results on a NVIDIA Jetson Xavier NX, and analyze the trade-offs between accuracy, robustness, model size, energy consumption, and training time. Our results demonstrate the construction of efficient, accurate, and robust networks entirely on an Edge device.
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。