期刊
APPLIED INTELLIGENCE
卷 49, 期 10, 页码 3570-3586出版社
SPRINGER
DOI: 10.1007/s10489-019-01468-7
关键词
Deep learning; Densely connected convolution networks; Model compression; Factorization technique; Image classification
资金
- National Natural Science Foundation of China [61772091, 61802035]
- Natural Science Foundation of Guangxi [2018GX NSFDA138005, 2016GXNSFAA380209, 2014GXNSFDA118037]
- Project of Scientific Research and Technology Development in Guangxi [AA18118047, AB16380272, AD18126015, 20175177]
- Innovation Project of Guangxi Graduate Education [YCSW2017187]
- Sichuan Science and Technology Program [2018JY0448, 2019YFG0106, 2019YFS0067]
- Innovative Research Team Construction Plan in Universities of Sichuan Province [18TD0027]
- Scientific Research Foundation for Young Academic Leaders of Chengdu University of Information Technology [J201701]
The main drawbacks of traditional densely connected convolution networks (DenseNet) lie in: complex network models, excessive parameters, a large amount of computational and storage resources, falling into the problem of over-fitting, resulting in low object recognition accuracy. In addition, in the field of fine-grained image classification, the recognition performance is insufficient due to the inadequate representation capability of extracting features. In order to cope with these problems, we propose a novel shallow densely connected convolution networks (called DenseNet-S), it works as: (1) we adopt a shallow network training strategy to degrade the computational complexity and reduce the parameters, in order to avoid excessive number of layers affecting the recognition accuracy; (2) we propose a novel squeeze method to further reduce the network parameters and effectively alleviate the over-fitting phenomena. In addition, we apply the fire module and add the squeeze layer and the expand layer to the convolution module in DenseNet; (3) we employ the factorization technique into small convolutions, which can partition a large two-dimensional convolution into two small one-dimensional convolutions, in order to improve the feature extraction capability and the recognition performance in fine-grained image classification. The effectiveness of DenseNet-S was evaluated by extensive experiments on three benchmark datasets including CIFAR-10, CIFAR-100 and SVHN.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据