Abstract
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing device-efficient ConvNets in less than 4 hours. 1. Novel NAS formulation: our method introduces a single-path, over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters. 2. NAS efficiency: Our method decreases the NAS search cost down to 8 epochs (30 TPU-hours), i.e., up to 5,000x faster compared to prior work. 3. On-device image classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms inference latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar latency (<80ms).
Abstract (translated)
在移动设备的延迟限制下，我们能自动设计一个具有最高图像分类精度的卷积网络吗？由于设计空间和搜索时间（至少200 gpu小时）的组合很大，神经网络结构搜索（NAS）是一个具有挑战性的问题。为了减轻这种复杂性，我们提出了一种新的可区分的单路径NAS方法，用于在不到4小时内设计设备有效的convnet。1。新的NAS公式：我们的方法引入了一个单路径的参数化convnet，用共享卷积核参数对所有的体系结构决策进行编码。2。NAS效率：我们的方法将NAS搜索成本降低到8个阶段（30 tpu小时），即比以前的工作快5000倍。三。设备上的图像分类：单路径NAS在ImageNet上的精确度达到74.96%，像素1手机上的推理延迟为79ms，与延迟相似（<80ms）的NAS方法相比，这是最先进的精确度。
URL
https://arxiv.org/abs/1905.04159
