Channel Pruning Guided by Classification Loss and Feature Importance

Authors

  • Jinyang Guo The University of Sydney
  • Wanli Ouyang The University of Sydney
  • Dong Xu The University of Sydney

DOI:

https://doi.org/10.1609/aaai.v34i07.6720

Abstract

In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach additionally take the classification loss into account in the channel pruning process. We also observe that some reconstructed features will be removed at the next pruning stage. So it is unnecessary to reconstruct these features. To this end, we propose a new strategy to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage). Our comprehensive experiments on three benchmark datasets, i.e., CIFAR-10, ImageNet, and UCF-101, demonstrate the effectiveness of our CPLI method.

Downloads

Published

2020-04-03

How to Cite

Guo, J., Ouyang, W., & Xu, D. (2020). Channel Pruning Guided by Classification Loss and Feature Importance. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 10885-10892. https://doi.org/10.1609/aaai.v34i07.6720

Issue

Section

AAAI Technical Track: Vision