Title: LightNet: pruned sparsed convolution neural network for image classification

Authors: Edna C. Too

Addresses: Department of Computer Science, Chuka University, Kenya

Abstract: Deep learning has become the most sought-after approach in the area of artificial intelligence (AI). However, deep learning models pose some challenges in the learning process. It is computationally intensive to train deep learning networks and also resource-intensive. Therefore, it cannot be applicable in limited-resource devices. Limited research is being done on the implementation of efficient approaches for real-world problems. This study tries to bridge the gaps towards an applicable system in the real world especially in the agricultural sector for plants disease management and fruits classification. We introduce a novel deep learning architecture called LightNet. LightNet is an architecture that employs two strategies to achieve the sparsity of DenseNet: the skip connections and pruning strategy. The resultant is a small network with reduced parameters and model size. LightNet model matches the performance of the highest accuracy of DenseNet. Moreover, LightNet is × 2 smaller, × 2 parameters efficient and × 3 faster compared original DenseNet. The model is evaluated on the real-worlds dataset PlantsVillage and Fruits-360. The results show that our model achieved state-of-the-art results and it can be used for plant disease detection and fruits classification and grading.

Keywords: LightNet; convolution neural network; CNN; convnets; deep learning; image classification; pruning; sparse networks; dense networks; neural network.

DOI: 10.1504/IJCSE.2023.131508

International Journal of Computational Science and Engineering, 2023 Vol.26 No.3, pp.283 - 295

Received: 27 May 2021
Received in revised form: 18 Nov 2021
Accepted: 27 Mar 2022
Published online: 15 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article