论文标题
MS-Ranas：多尺度资源感知的神经体系结构搜索
MS-RANAS: Multi-Scale Resource-Aware Neural Architecture Search
论文作者
论文摘要
事实证明，神经建筑搜索（NAS）在提供手工神经网络的替代方案方面有效。在本文中，我们分析了NAS在严格的计算约束下对图像分类任务的好处。我们的目的是自动化高效的深层神经网络的设计，能够提供快速，准确的预测，并且可以在低内存，低功率的芯片上部署。因此，任务成为准确性，计算复杂性和内存要求之间的三方权衡。为了解决这个问题，我们建议多尺度的资源感知的神经体系结构搜索（MS-Ranas）。我们采用一种单次架构搜索方法来获得降低的搜索成本，我们专注于任何时间预测设置。通过使用多个尺度功能和早期分类器，我们在准确速度权衡方面取得了最新的结果。
Neural Architecture Search (NAS) has proved effective in offering outperforming alternatives to handcrafted neural networks. In this paper we analyse the benefits of NAS for image classification tasks under strict computational constraints. Our aim is to automate the design of highly efficient deep neural networks, capable of offering fast and accurate predictions and that could be deployed on a low-memory, low-power system-on-chip. The task thus becomes a three-party trade-off between accuracy, computational complexity, and memory requirements. To address this concern, we propose Multi-Scale Resource-Aware Neural Architecture Search (MS-RANAS). We employ a one-shot architecture search approach in order to obtain a reduced search cost and we focus on an anytime prediction setting. Through the usage of multiple-scaled features and early classifiers, we achieved state-of-the-art results in terms of accuracy-speed trade-off.
