Recent works on Binary Neural Networks (BNNs) have made promising progress in
narrowing the accuracy gap of BNNs to their 32-bit counterparts. However, the
accuracy gains are often based on specialized model designs using additional
32-bit components. Furthermore, almost all previous BNNs use 32-bit for feature
maps and the shortcuts enclosing the corresponding binary convolution blocks,
which helps to effectively maintain the accuracy, but is not friendly to
hardware accelerators with limited memory, energy, and computing resources.
Thus, we raise the following question: How can accuracy and energy consumption
be balanced in a BNN network design? We extensively study this fundamental
problem in this work and propose a novel BNN architecture without most commonly
used 32-bit components: \textit{BoolNet}. Experimental results on ImageNet
demonstrate that BoolNet can achieve 4.6x energy reduction coupled with 1.2\%
higher accuracy than the commonly used BNN architecture Bi-RealNet. Code and
trained models are available at: this https URL

本文提出了一种名为 BoolNet 的二值神经网络（BNN）架构，该架构不使用常见的 32 位组件，能够在不影响准确性的情况下减少能源消耗，并且与现有的 BNN 架构 Bi-RealNet 相比，能够获得高达 1.2% 的额外准确性和 4.6 倍的能量降低。