D-Score: A Synapse-Inspired Approach for Filter Pruning

08/08/2023

∙

This paper introduces a new aspect for determining the rank of the unimportant filters for filter pruning on convolutional neural networks (CNNs). In the human synaptic system, there are two important channels known as excitatory and inhibitory neurotransmitters that transmit a signal from a neuron to a cell. Adopting the neuroscientific perspective, we propose a synapse-inspired filter pruning method, namely Dynamic Score (D-Score). D-Score analyzes the independent importance of positive and negative weights in the filters and ranks the independent importance by assigning scores. Filters having low overall scores, and thus low impact on the accuracy of neural networks are pruned. The experimental results on CIFAR-10 and ImageNet datasets demonstrate the effectiveness of our proposed method by reducing notable amounts of FLOPs and Params without significant Acc. Drop.

READ FULL TEXT

D-Score: A Synapse-Inspired Approach for Filter Pruning

Data Agnostic Filter Gating for Efficient Deep Networks

Batch Normalization Tells You Which Filter is Important

Neural Network Pruning for Real-time Polyp Segmentation

Dynamic Weight Alignment for Convolutional Neural Networks

Provable Filter Pruning for Efficient Neural Networks

Neuron ranking -- an informed way to condense convolutional neural networks architecture

Dependency Aware Filter Pruning

D-Score: A Synapse-Inspired Approach for Filter Pruning

Related Research

Data Agnostic Filter Gating for Efficient Deep Networks

Batch Normalization Tells You Which Filter is Important

Neural Network Pruning for Real-time Polyp Segmentation

Dynamic Weight Alignment for Convolutional Neural Networks

Provable Filter Pruning for Efficient Neural Networks

Neuron ranking -- an informed way to condense convolutional neural networks architecture

Dependency Aware Filter Pruning