Balanced Binary Neural Networks with Gated Residual

Abstract

Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the accuracy of networks still remains a critical issue. In this paper, we attempt to maintain the information propagated in the forward process and propose a Balanced Binary Neural Networks with Gated Residual (BBG for short). First, a weight balanced binarization is introduced to maximize information entropy of binary weights, and thus the informative binary weights can capture more information contained in the activations. Second, for binary activations, a gated residual is further appended to compensate their information loss during the forward process, with a slight overhead. Both techniques can be wrapped as a generic network module that supports various network architectures for different tasks including classification and detection. We evaluate our BBG on image classification tasks over CIFAR-10/100 and ImageNet and on detection task over Pascal VOC. The experimental results show that BBG-Net performs remarkably well across various network architectures such as VGG, ResNet and SSD with the superior performance over state-of-the-art methods in terms of memory consumption, inference speed and accuracy.

arXiv commentAccepted by ICASSP2020

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Squeeze-and-Excitation Networks
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Binarized Neural Networks
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• Compressing Neural Networks with the Hashing Trick
• Highway Networks
• Towards Accurate Binary Convolutional Neural Network
• Loss-aware Weight Quantization of Deep Networks
• Deep Learning with Low Precision by Half-wave Gaussian Quantization
• Back to Simplicity: How to Train Accurate BNNs from Scratch?
• Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
• Attribute Aware Pooling for Pedestrian Attribute Recognition
• Towards Evolutional Compression
• daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices
• Searching for Accurate Binary Neural Architectures