We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bitwise operations, leading to much faster test-time inference and lower power consumption. However, previous works on binarizing CNNs usually result in severe prediction accuracy degradation. In this paper, we address this issue with two major innovations: (1) approximating full-precision weights with the linear combination of multiple binary weight bases; (2) employing multiple binary activations to alleviate information loss. The implementation of the resulting binary CNN, denoted as ABC-Net, is shown to achieve much closer performance to its full-precision counterpart, and even reach the comparable prediction accuracy on ImageNet and forest trail datasets, given adequate binary weight bases and activations.

本文引入了一种新颖的方案来训练二值卷积神经网络，使用多个二元权重基的线性组合逼近完全精度权重，并采用多个二元激活来减轻信息丢失的问题，最终实现了一个二值卷积神经网络（ABC-Net），能够在适当的二元权重和激活函数基础上，取得与全精度神经网络相当的预测准确性。

朝着精准二值卷积神经网络