Network binarization is a promising hardware-aware direction for creating efficient deep models. Despite its memory and computational advantages, reducing the accuracy gap between binary models and their real-valued counterparts remains an unsolved challenging research problem. To this end, we make the following 3 contributions: (a) To increase model capacity, we propose Expert Binary Convolution, which, for the first time, tailors conditional computing to binary networks by learning to select one data-specific expert binary filter at a time conditioned on input features. (b) To increase representation capacity, we propose to address the inherent information bottleneck in binary networks by introducing an efficient width expansion mechanism which keeps the binary operations within the same budget. (c) To improve network design, we propose a principled binary network growth mechanism that unveils a set of network topologies of favorable properties. Overall, our method improves upon prior work, with no increase in computational cost, by $\sim6 \%$, reaching a groundbreaking $\sim 71\%$ on ImageNet classification. Code will be made available $\href{https://www.adrianbulat.com/binary-networks}{here}$.

翻译：网络二进制是创建高效深层模型的一个充满希望的硬件认知方向。尽管它具有记忆和计算优势,但缩小二进制模型与实际价值对等模型之间的准确性差距仍然是一个难以解决的棘手研究问题。为此,我们提出以下3项贡献:(a) 为提高模型能力,我们建议专家二进制进化,我们首次通过学习选择一个特定数据的专家二进制过滤器,在以输入功能为条件时,将有条件计算成二进制网络。 (b) 为提高代表能力,我们提议通过引入高效的宽度扩展机制,将二进制操作保留在同一预算之内,解决二进制网络中固有的信息瓶颈问题。 (c) 为改进网络设计,我们提议了一个有原则的双进化网络机制,以揭开一套有利属性的网络结构。总体而言,我们的方法在以往工作的基础上改进了方法,没有增加计算成本,每增加1美元,在图像网络分类上达到破碎的$71 ⁇ 美元。 将提供代码 $\href{www_adrianatcom.