A survey on image classification of lightweight convolutional neural network

- Liu, Ying, Xiao, Peng, Fang, Jie, Zhang, Dengsheng

Title
A survey on image classification of lightweight convolutional neural network
Creator
Liu, Ying; Xiao, Peng; Fang, Jie; Zhang, Dengsheng
Date
2023
Type
Text; Conference paper
Identifier
http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/196997
Identifier
vital:18787
Identifier
https://doi.org/10.1109/ICNC-FSKD59587.2023.10281072
Identifier
ISBN:9798350304398 (ISBN)
Abstract
In recent years, deep neural networks have achieved tremendous success in image classification in both academic and industrial settings. However, the high hardware requirements imposed by their intensive and complex computations pose a challenge for deployment on low-storage devices. To address this challenge, lightweight networks provide a viable solution. This paper provides a detailed review of recent lightweight image classification algorithms, which can be categorized into low-redundancy network model design and neural network compression algorithms. The former reduces network computations by replacing traditional convolution with efficient lightweight convolution, while the latter reduces redundancy in the network by employing methods such as network pruning, knowledge distillation, and parameter quantization. We summarize the experimental results of some classical models and algorithms on ImageNet2012 and CIFAR-10 datasets, and analyze the characteristics, advantages and disadvantages of these models respectively. Finally, future research directions for lightweight algorithms in the field of image classification are identified. © 2023 IEEE.
Publisher
Institute of Electrical and Electronics Engineers Inc.
Relation
19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2023, Harbin, China, 29-31 July 2023, 2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)
Rights
All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
Rights
Copyright © 2023 IEEE
Subject
Deep neural networks; Efficient lightweight convolution; Image classification; Lightweight networks; Network compression
Reviewed
  • Hits: 643
  • Visitors: 636
  • Downloads: 0
Thumbnail File Description Size Format