Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy

TL;DR

This paper introduces a method for ternarizing deep CNN weights to significantly reduce model size and computation, while maintaining or improving accuracy on CIFAR-10 and ImageNet datasets.

Contribution

It proposes statistical weight scaling and residual expansion techniques for effective ternarization, achieving high compression rates with minimal accuracy loss or gains.

Findings

Achieves 16x model compression with slight accuracy improvements on CIFAR-10.

Outperforms recent methods on ImageNet with similar compression rates.

Further residual expansion improves top-5 accuracy with minimal top-1 degradation.

Abstract

Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited embedded systems. As the countermeasure to this problem, in this work, we propose statistical weight scaling and residual expansion methods to reduce the bit-width of the whole network weight parameters to ternary values (i.e. -1, 0, +1), with the objectives to greatly reduce model size, computation cost and accuracy degradation caused by the model compression. With about 16x model compression rate, our ternarized ResNet-32/44/56 could outperform full-precision counterparts by 0.12%, 0.24% and 0.18% on CIFAR- 10 dataset. We also test our ternarization method with AlexNet and ResNet-18 on ImageNet dataset, which both achieve the best top-1 accuracy compared to recent similar works, with the same 16x compression rate. If further incorporating our residual expansion method, compared to the full-precision counterpart, our ternarized ResNet-18 even improves the top-5 accuracy by 0.61% and merely degrades the top-1 accuracy only by 0.42% for the ImageNet dataset, with 8x model compression rate. It outperforms the recent ABC-Net by 1.03% in top-1 accuracy and 1.78% in top-5 accuracy, with around 1.25x higher compression rate and more than 6x computation reduction due to the weight sparsity.