Accelerating Convolutional Neural Network Pruning via Spatial Aura Entropy
This work addresses computational bottlenecks in CNN pruning for model compression, but it is incremental as it builds on existing mutual information methods.
The paper tackled the problem of high computational cost and noise sensitivity in mutual information computation for CNN pruning, proposing a spatial aura entropy method that improved pruning performance and efficiency on CIFAR-10.
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.