Accelerating Convolutional Neural Network Pruning via Spatial Aura Entropy

TL;DR

This paper introduces a new CNN pruning method that uses spatial aura entropy to improve mutual information computation, resulting in more efficient and effective model compression.

Contribution

It presents a novel spatial aura entropy technique to enhance mutual information calculation for CNN pruning, addressing computational cost and noise sensitivity issues.

Findings

Outperforms existing methods on CIFAR-10 in pruning efficiency

Reduces computational cost of MI calculation

Achieves more robust pruning results

Abstract

In recent years, pruning has emerged as a popular technique to reduce the computational complexity and memory footprint of Convolutional Neural Network (CNN) models. Mutual Information (MI) has been widely used as a criterion for identifying unimportant filters to prune. However, existing methods for MI computation suffer from high computational cost and sensitivity to noise, leading to suboptimal pruning performance. We propose a novel method to improve MI computation for CNN pruning, using the spatial aura entropy. The spatial aura entropy is useful for evaluating the heterogeneity in the distribution of the neural activations over a neighborhood, providing information about local features. Our method effectively improves the MI computation for CNN pruning, leading to more robust and efficient pruning. Experimental results on the CIFAR-10 benchmark dataset demonstrate the superiority of our approach in terms of pruning performance and computational efficiency.