Binarized convolutional neural networks (BCNNs) are widely used to improve
memory and computation efficiency of deep convolutional neural networks (DCNNs)
for mobile and AI chips based applications. However, current BCNNs are not able
to fully explore their corresponding full-precision models, causing a
significant performance gap between them. In this paper, we propose rectified
binary convolutional networks (RBCNs), towards optimized BCNNs, by combining
full-precision kernels and feature maps to rectify the binarization process in
a unified framework. In particular, we use a GAN to train the 1-bit binary
network with the guidance of its corresponding full-precision model, which
significantly improves the performance of BCNNs. The rectified convolutional
layers are generic and flexible, and can be easily incorporated into existing
DCNNs such as WideResNets and ResNets. Extensive experiments demonstrate the
superior performance of the proposed RBCNs over state-of-the-art BCNNs. In
particular, our method shows strong generalization on the object tracking task.

本文提出一种名为修正二值卷积网络（RBCNs）的优化二值卷积神经网络的方法，通过结合全精度卷积核和特征图在统一框架内实现二值化过程的校正，并使用生成对抗网络（GAN）以其相应的全精度模型为指导来训练 1 位二进制网络，从而显著提高了 BCNN 的性能。该方法的可塑性强，并可轻松纳入现有的 DCNN 中，如 WideResNets 和 ResNets。大量实验表明，所提出的 RBCNs 比最先进的 BCNNs 具有优越的性能，并在物体跟踪任务中显示了强大的泛化能力。