Dual sparse training framework: inducing activation map sparsity via Transformed $\ell1$ regularization

TL;DR

This paper introduces a dual sparse training framework using Transformed ℓ1 regularization to induce activation map sparsity, significantly reducing computational load and storage needs in deep CNNs without sacrificing accuracy.

Contribution

It proposes a novel dual sparse training framework that combines activation sparsity induction with traditional pruning, achieving higher sparsity and efficiency across various models.

Findings

Achieves over 20% increase in activation map sparsity on most models.

Reduces 81.7% and 84.13% of FLOPs in ResNet18 and ResNet50 respectively.

Maintains accuracy while significantly decreasing computational and storage requirements.

Abstract

Although deep convolutional neural networks have achieved rapid development, it is challenging to widely promote and apply these models on low-power devices, due to computational and storage limitations. To address this issue, researchers have proposed techniques such as model compression, activation sparsity induction, and hardware accelerators. This paper presents a method to induce the sparsity of activation maps based on Transformed $\ell1$ regularization, so as to improve the research in the field of activation sparsity induction. Further, the method is innovatively combined with traditional pruning, constituting a dual sparse training framework. Compared to previous methods, Transformed $\ell1$ can achieve higher sparsity and better adapt to different network structures. Experimental results show that the method achieves improvements by more than 20\% in activation map sparsity on most models and corresponding datasets without compromising the accuracy. Specifically, it achieves a 27.52\% improvement for ResNet18 on the ImageNet dataset, and a 44.04\% improvement for LeNet5 on the MNIST dataset. In addition, the dual sparse training framework can greatly reduce the computational load and provide potential for reducing the required storage during runtime. Specifically, the ResNet18 and ResNet50 models obtained by the dual sparse training framework respectively reduce 81.7\% and 84.13\% of multiplicative floating-point operations, while maintaining accuracy and a low pruning rate.