DeepAI AI Chat
Log In Sign Up

Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks

by   Souvik Kundu, et al.

The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices. This work introduces convolutional layers with pre-defined sparse 2D kernels that have support sets that repeat periodically within and across filters. Due to the efficient storage of our periodic sparse kernels, the parameter savings can translate into considerable improvements in energy efficiency due to reduced DRAM accesses, thus promising significant improvements in the trade-off between energy consumption and accuracy for both training and inference. To evaluate this approach, we performed experiments with two widely accepted datasets, CIFAR-10 and Tiny ImageNet in sparse variants of the ResNet18 and VGG16 architectures. Compared to baseline models, our proposed sparse variants require up to 82 5.6times fewer FLOPs with negligible loss in accuracy for ResNet18 on CIFAR-10. For VGG16 trained on Tiny ImageNet, our approach requires 5.8times fewer FLOPs and up to 83.3 only 1.2 architectures with that of ShuffleNet andMobileNetV2. Using similar hyperparameters and FLOPs, our ResNet18 variants yield an average accuracy improvement of 2.8


page 5

page 12

page 13

page 14


A Pre-defined Sparse Kernel Based Convolutionfor Deep CNNs

The high demand for computational and storage resources severely impede ...

A Pre-defined Sparse Kernel Based Convolution for Deep CNNs

The high demand for computational and storage resources severely impede ...

Learning Sparse Filters in Deep Convolutional Neural Networks with a l1/l2 Pseudo-Norm

While deep neural networks (DNNs) have proven to be efficient for numero...

Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation

The advancement of deep convolutional neural networks (DCNNs) has driven...

SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks

Binary Convolutional Neural Networks (BCNNs) can significantly improve t...

Code Repositories


This repository constains a Pytorch implementation of the paper, titled "Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks"

view repo