Rethinking the Smaller-Norm-Less-Informative Assumption
in Channel Pruning of Convolution Layers
Jianbo Ye (1), Xin Lu (2), Zhe Lin (2) and James Z. Wang (1)
(1) The Pennsylvania State University
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a smaller-norm parameter or feature plays a less informative role at the inference time. In this paper, we propose a channel pruning technique for accelerating the computations of deep convolutional neural networks (CNNs) that does not critically rely on this assumption. Instead, it focuses on direct simplification of the channel-to-channel computation graph of a CNN without the need of performing a computationally difficult and not-always-useful task of making high-dimensional tensors of CNN structured sparse. Our approach takes two stages: first to adopt an end-to-end stochastic training method that eventually forces the outputs of some channels to be constant, and then to prune those constant channels from the original neural network by adjusting the biases of their impacting layers such that the resulting compact model can be quickly fine-tuned. Our approach is mathematically appealing from an optimization perspective and easy to reproduce. We experimented our approach through several image learning benchmarks and demonstrate its interesting aspects and competitive performance.
Jianbo Ye, Xin Lu, Zhe Lin and James Z. Wang, ``Rethinking the
Smaller-Norm-Less-Informative Assumption in Channel Pruning of
Convolution Layers,'' Proceedings of the International Conference on
Learning Representation, 11 pages, Vancouver, Canada, May 2018.
© 2018 ICLR. Personal use of this material is permitted. However,
permission to reprint/republish this material for advertising or
promotional purposes or for creating new collective works for resale
or redistribution to servers or lists, or to reuse any copyrighted
component of this work in other works must be obtained from the ICLR.
February 3, 2018