This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers. A key but fairly overlooked feature of the current state-of-the-art method of XNOR-Net is the use of analytically calculated real-valued scaling factors for re-weighting the output of binary convolutions. We argue that analytic calculation of these factors is sub-optimal. Instead, in this work, we make the following contributions: (a) we propose to fuse the activation and weight scaling factors into a single one that is learned discriminatively via backpropagation. (b) More importantly, we explore several ways of constructing the shape of the scale factors while keeping the computational budget fixed. (c) We empirically measure the accuracy of our approximations and show that they are significantly more accurate than the analytically calculated one. (d) We show that our approach significantly outperforms XNOR-Net within the same computational budget when tested on the challenging task of ImageNet classification, offering up to 6\% accuracy gain.

本文提出了一种改进的训练算法，用于针对二元神经网络的权重和激活二进制数的训练，提出了一种新的比XNOR-Net更优的方法，通过反向传播学习判别式融合激活和权重缩放因子。实验表明，与分析计算的结果相比，我们的方法更加准确，且在相同的计算预算下，可在 ImageNet 分类任务中提供高达 6% 的准确性提升。

XNOR-Net++: 二值神经网络的改进