Tseng Fan-Hsun, Yeh Kuo-Hui, Kao Fan-Yi, Chen Chi-Yuan
Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.
Department of Information Management, National Dong Hwa University, Hualien, Taiwan; Computer Science and Engineering Department of National Sun Yat-sen University, Kaohsiung 804, Taiwan.
ISA Trans. 2023 Jan;132:120-130. doi: 10.1016/j.isatra.2022.07.030. Epub 2022 Aug 18.
In recent years, artificial intelligence (AI) has been developed vigorously, and a great number of AI autonomous applications have been proposed. However, how to decrease computations and shorten training time with high accuracy under the limited hardware resource is a vital issue. In this paper, on the basis of MobileNet architecture, the dense squeeze with depthwise separable convolutions model is proposed, viz. MiniNet. MiniNet utilizes depthwise and pointwise convolutions, and is composed of the dense connection technique and the Squeeze-and-Excitation operations. The proposed MiniNet model is implemented and experimented with Keras. In experimental results, MiniNet is compared with three existing models, i.e., DenseNet, MobileNet, and SE-Inception-Resnet-v1. To validate that the proposed MiniNet model is provided with less computation and shorter training time, two types as well as large and small datasets are used. The experimental results showed that the proposed MiniNet model significantly reduces the number of parameters and shortens training time efficiently. MiniNet is superior to other models in terms of the lowest parameters, shortest training time, and highest accuracy when the dataset is small, especially.
近年来，人工智能（AI）蓬勃发展，大量人工智能自主应用被提出。然而，在有限的硬件资源下如何以高精度减少计算量并缩短训练时间是一个至关重要的问题。本文基于MobileNet架构，提出了一种具有深度可分离卷积的密集挤压模型，即MiniNet。MiniNet利用深度卷积和逐点卷积，由密集连接技术和挤压激励操作组成。所提出的MiniNet模型使用Keras进行了实现和实验。在实验结果中，将MiniNet与三种现有模型进行了比较，即DenseNet、MobileNet和SE-Inception-Resnet-v1。为了验证所提出的MiniNet模型具有更少的计算量和更短的训练时间，使用了两种类型以及大小不同的数据集。实验结果表明，所提出的MiniNet模型显著减少了参数数量，并有效缩短了训练时间。特别是在数据集较小时，MiniNet在参数最少、训练时间最短和准确率最高方面优于其他模型。
