This paper proposes Binary ArchitecTure Search (BATS), a framework that
drastically reduces the accuracy gap between binary neural networks and their
real-valued counterparts by means of Neural Architecture Search (NAS). We show
that directly applying NAS to the binary domain provides very poor results. To
alleviate this, we describe, to our knowledge, for the first time, the 3 key
ingredients for successfully applying NAS to the binary domain. Specifically,
we (1) introduce and design a novel binary-oriented search space, (2) propose a
new mechanism for controlling and stabilising the resulting searched
topologies, (3) propose and validate a series of new search strategies for
binary networks that lead to faster convergence and lower search times.
Experimental results demonstrate the effectiveness of the proposed approach and
the necessity of searching in the binary space directly. Moreover, (4) we set a
new state-of-the-art for binary neural networks on CIFAR10, CIFAR100 and
ImageNet datasets. Code will be made available
this https URL

本文提出了 Binary ArchitecTure Search (BATS) 框架，并提出了三种成功应用 NAS 到二进制领域的关键要素，包括引入二进制导向搜索空间，提出控制和稳定搜索拓扑的新机制，以及提出验证了的能导致更快收敛和较低搜索时间的一系列新的二进制网络搜索策略。实验结果表明所提出的方法的有效性和直接在二进制空间中进行搜索的必要性，同时还在 CIFAR10、CIFAR100 和 ImageNet 数据集上创造了新的二进制神经网络的最新技术水平。