Abstract
Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential solutions. Neural architecture search (NAS) methods automatically search the space of neural network hyperparameters in order to find optimal task-specific architectures. NAS methods have discovered CNN architectures that achieve state-of-the-art performance in image classification among other tasks, however the application of NAS to image-to-image regression problems such as image restoration is sparse. This paper proposes a NAS method that performs computationally efficient evolutionary search of a minimally constrained network architecture search space. The performance of architectures discovered by the proposed method is evaluated on a variety of image restoration tasks applied to the ImageNet64x64 dataset, and compared with human-engineered CNN architectures. The best neural architectures discovered using only 2 GPU-hours of evolutionary search exhibit comparable performance to the human-engineered baseline architecture.
Abstract (translated)
卷积神经网络(CNN)的结构传统上是由人类专家在人工搜索过程中探索的,这是一个耗时且效率低下的探索潜在解决方案的巨大空间的过程。神经网络结构搜索(NAS)方法自动搜索神经网络超参数的空间,以找到最优的任务特定结构。NAS方法已经发现了CNN体系结构,它在图像分类等任务中实现了最先进的性能,但是在图像到图像的回归问题(如图像恢复)中,NAS的应用却很少。本文提出了一种对最小约束网络体系结构搜索空间进行计算高效的进化搜索的NAS方法。通过应用于ImageNet64X64数据集的各种图像恢复任务,对该方法发现的体系结构的性能进行了评估,并与人工CNN体系结构进行了比较。仅使用2个GPU小时的进化搜索发现的最佳神经架构表现出与人类工程基线架构相当的性能。
URL
https://arxiv.org/abs/1812.05866