Filters








1 Hit in 0.052 sec

Feature Statistics Guided Efficient Filter Pruning

Hang Li, Chen Ma, Wei Xu, Xue Liu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods delete part of the CNN filters according to some metrics such as l1-norm. However, previous methods hardly leverage the information variance in a single feature map and the similarity characteristics among feature maps. In this paper, we propose a novel
more » ... opose a novel filter pruning method, which incorporates two kinds of feature map selections: diversity-aware selection (DFS) and similarity-aware selection (SFS). DFS aims to discover features with low information diversity while SFS removes features that have high similarities with others. We conduct extensive empirical experiments with various CNN architectures on publicly available datasets. The experimental results demonstrate that our model obtains up to 91.6% parameter decrease and 83.7% FLOPs reduction with almost no accuracy loss.
doi:10.24963/ijcai.2020/359 dblp:conf/ijcai/LuoZLZWXFS20 fatcat:2hj4lgkc2fbwtisdoq5wiscy6q