Linear Combination Approximation of Feature for Channel Pruning

Abstract

Network pruning is an effective method that reduces the computation of neural networks while maintaining high performance. This enables the operation of deep neural networks in resource-limited environments. In a general large network, the roles of each channel often inevitably overlap with those of others. Therefore, for more effective pruning, it is important to observe the correlation between features in the network. In this paper, we propose a novel channel pruning method, namely, the linear combination approximation of features (LCAF). We approximate each feature map by a linear combination of other feature maps in the same layer, and then remove the most approximated one. Additionally, by exploiting the linearity of the convolution operation, we propose a supporting method called weight modification, to further reduce the loss change that occurs during pruning. Extensive experiments show that LCAF achieves state-of-the-art performance in several benchmarks. Furthermore, ablations on the LCAF demonstrate the effectiveness of our approach in a variety of ways.