Carrying out CNN Channel Pruning in a White Box
Yuxin Zhang, Mingbao Lin, Chia-Wen Lin, Jie Chen, Feiyue Huang,, Yongjian Wu, Yonghong Tian, Rongrong Ji

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning
MethodsPruning
