Compact Deep Convolutional Neural Networks With Coarse Pruning

Abstract

The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature map and kernel level pruning for reducing the computational complexity of a deep convolutional neural network. Pruning feature maps reduces the width of a layer and hence does not need any sparse representation. Further, kernel pruning converts the dense connectivity pattern into a sparse one. Due to coarse nature, these pruning granularities can be exploited by GPUs and VLSI based implementations. We propose a simple and generic strategy to choose the least adversarial pruning masks for both granularities. The pruned networks are retrained which compensates the loss in accuracy. We obtain the best pruning ratios when we prune a network with both granularities. Experiments with the CIFAR-10 dataset show that more than 85% sparsity can be induced in the convolution layers with less than 1% increase in the missclassification rate of the baseline network.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Pruning Filters for Efficient ConvNets
• Memory Bounded Deep Convolutional Networks

Cited by in corpus (6)

• Channel Pruning for Accelerating Very Deep Neural Networks
• Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications
• Structured Pruning for Efficient ConvNets via Incremental Regularization
• Compressing complex convolutional neural network based on an improved deep compression algorithm
• Synthesis and Pruning as a Dynamic Compression Strategy for Efficient Deep Neural Networks
• A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks