30/11/2020

Channel Pruning for Accelerating Convolutional Neural Networks via Wasserstein Metric

Haoran Duan, Hui Li

Keywords:

Abstract Paper Similar Papers

Abstract: Channel pruning is an effective way to accelerate deep convolutional neural networks. However, it is still a challenge to reduce the computational complexity while preserving the performance of deep models. In this paper, we propose a novel channel pruning method via the Wasserstein metric. First, the output features of a channel are aggregated through the Wasserstein barycenter, which is called the basic response of the channel. Then the channel discrepancy based on the Wasserstein distance is introduced to measure channel importance, by considering both the channel's feature representation ability and the substitutability of the basic responses. Finally, channels with the least discrepancies are removed directly, and the loss in accuracy of the pruned model is regained by fine-tuning. Extensive experiments on popular benchmarks and various network architectures demonstrate that the proposed approach outperforms the existing methods.

The video of this talk cannot be embedded. You can watch it here:
https://accv2020.github.io/miniconf/poster_224.html
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 10:07 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 1
 9:32 
 0
 0
 0
 0
 2:50 
 0
 0
 0
 0
 8:13 
 0
 0
 0
 0
 4:16 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 4:30 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 7:57 
 0
 0
 0
 0
 13:48 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 11:01 
 0
 0
 0
 0
 20:21 
 0
 0
 0
 0
 5:51 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 5:09 
 1
 0
 0
 0
 5:11 
 0
 0
 0
 0
 14:44 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 4:23 
 0
 0
 0
 0
 5:30 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 10:33 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 4:47 
 1
 0
 0
 0
 14:01