Loading...

Lightweight residual densely connected convolutional neural network

Fooladgar, F ; Sharif University of Technology | 2020

399 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/s11042-020-09223-8
  3. Publisher: Springer , 2020
  4. Abstract:
  5. Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints of these devices. Recently, some architectures have been proposed to overcome these limitations by considering specific hardware-software equipment. In this paper, the lightweight residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed method decreases the cost of training and inference processes without using any special hardware-software equipment by just reducing the number of parameters and computational operations while achieving a feasible accuracy. Extensive experimental results demonstrate that the proposed architecture is more efficient than the AlexNet and VGGNet in terms of model size, required parameters, and even accuracy. The proposed model has been evaluated on the ImageNet, MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. It achieves state-of-the-art results on Fashion MNIST dataset and reasonable results on the others. The obtained results show the superiority of the proposed method to efficient models such as the SqueezNet. It is also comparable with state-of-the-art efficient models such as CondenseNet and ShuffleNet. © 2020, Springer Science+Business Media, LLC, part of Springer Nature
  6. Keywords:
  7. Convolutional neural networks ; Deep learning ; Efficient architecture ; Image classification ; Convolution ; Network architecture ; Computational operations ; Embedded and mobile devices ; Inference process ; Proposed architectures ; Software equipment ; Special hardware ; Specific hardware ; State of the art
  8. Source: Multimedia Tools and Applications ; Volume 79, Issue 35-36 , 2020 , Pages 25571-25588
  9. URL: https://link.springer.com/article/10.1007/s11042-020-09223-8