Carrying out CNN Channel Pruning in a White Box

TL;DR

This paper introduces a white-box CNN channel pruning method guided by interpretability, which preserves channels based on their contribution to categories, leading to significant FLOPs reduction with minimal accuracy loss.

Contribution

It is the first to incorporate CNN interpretability theory into channel pruning, using class-wise masks and a voting mechanism for more informed pruning decisions.

Findings

Reduces 65.23% FLOPs on CIFAR-10 with 0.62% accuracy gain

Achieves 45.6% FLOPs reduction on ImageNet with 0.83% accuracy loss

Outperforms many state-of-the-art pruning methods

Abstract

Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this paper, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w.r.t. the input image's category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments on representative image classification tasks demonstrate the superiority of our White-Box over many state-of-the-arts. For instance, on CIFAR-10, it reduces 65.23% FLOPs with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOPs reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50.