Deep convolutional neural network based on densely connected squeeze-and-excitation blocks

被引:8
|
作者
Wu, Yu [1 ]
机构
[1] Guangzhou Univ, Lab Ctr, Guangzhou 510006, Guangdong, Peoples R China
关键词
CNN;
D O I
10.1063/1.5100577
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
Convolutional neural networks have achieved great successes in many visual tasks, as well as a good performance in various applications. However, research has yet to solve the practical problem of how to improve the recognition rate by increasing the depth of the network. The method proposed in this paper is based on the idea of a residual network, which shows that if a fast connection is added between network layers, the network will be deeper, the accuracy will be higher, and the training will be more efficient. The proposed Densely Squeeze-and-Excitation Network (DSENet) combines densely connected networks with the structure of a Squeeze-and-Excitation Network (SENet). The proposed structure is based on layers comprising blocks of compressed networks, and DSENet enables each of these layers to connect directly to all previous layers with adaptive weights. DSENet has many advantages, such as a high utilization rate of parameters and the ability to alleviate the disappearance of a gradient. The performance of the proposed network is evaluated on the CIFAR-10 and CIFAR-100 datasets, and experiments show that DSENet achieves better results on those datasets when compared with the most popular convolutional networks in current use.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Aggregated squeeze-and-excitation transformations for densely connected convolutional networks
    Yang, Mingming
    Ma, Tinghuai
    Tian, Qing
    Tian, Yuan
    Al-Dhelaan, Abdullah
    Al-Dhelaan, Mohammed
    [J]. VISUAL COMPUTER, 2022, 38 (08): : 2661 - 2674
  • [2] Aggregated squeeze-and-excitation transformations for densely connected convolutional networks
    Mingming Yang
    Tinghuai Ma
    Qing Tian
    Yuan Tian
    Abdullah Al-Dhelaan
    Mohammed Al-Dhelaan
    [J]. The Visual Computer, 2022, 38 : 2661 - 2674
  • [3] Focus prediction of medical microscopic images based on Lightweight Densely Connected with Squeeze-and-Excitation Network
    Jiang, Hesong
    Ma, Li
    Wang, Xueyuan
    Zhang, Juan
    Liu, Yueyue
    Wang, Dan
    Wu, Peihong
    Han, Wanfen
    [J]. FRONTIERS IN NEUROSCIENCE, 2023, 17
  • [4] Image Steganalysis via Diverse Filters and Squeeze-and-Excitation Convolutional Neural Network
    Liu, Feng
    Zhou, Xuan
    Yan, Xuehu
    Lu, Yuliang
    Wang, Shudong
    [J]. MATHEMATICS, 2021, 9 (02) : 1 - 13
  • [5] Squeeze-and-Excitation Convolutional Neural Network for Classification of Malignant and Benign Lung Nodules
    Chen, Ying
    Du, Weiwei
    Duan, Xiaojie
    Ma, Yanhe
    Zhang, Hong
    [J]. JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY, 2021, 12 (02) : 153 - 158
  • [6] Convolutional squeeze-and-excitation network for ECG arrhythmia detection
    Ge, Rongjun
    Shen, Tengfei
    Zhou, Ying
    Liu, Chengyu
    Zhang, Libo
    Yang, Benqiang
    Yan, Ying
    Coatrieux, Jean-Louis
    Chen, Yang
    [J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2021, 121
  • [7] Deep Squeeze and Excitation-Densely Connected Convolutional Network with cGAN for Alzheimer's Disease Early Detection
    Kadri, Rahma
    Tmar, Mohamed
    Bouaziz, Bassem
    Gargouri, Faiez
    [J]. INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, ISDA 2021, 2022, 418 : 441 - 451
  • [8] A Multi-Branch Convolutional Neural Network with Squeeze-and-Excitation Attention Blocks for EEG-Based Motor Imagery Signals Classification
    Altuwaijri, Ghadir Ali
    Muhammad, Ghulam
    Altaheri, Hamdi
    Alsulaiman, Mansour
    [J]. DIAGNOSTICS, 2022, 12 (04)
  • [9] Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention
    Lu, Zhenzhen
    Miao, Jingpeng
    Dong, Jingran
    Zhu, Shuyuan
    Wu, Penghan
    Wang, Xiaobing
    Feng, Jihong
    [J]. TRANSLATIONAL VISION SCIENCE & TECHNOLOGY, 2023, 12 (01):
  • [10] Biometric Fish Classification of Temperate Species Using Convolutional Neural Network with Squeeze-and-Excitation
    Olsvik, Erlend
    Trinh, Christian M. D.
    Knausgard, Kristian Muri
    Wiklund, Arne
    Sordalen, Tonje Knutsen
    Kleiven, Alf Ring
    Jiao, Lei
    Goodwin, Morten
    [J]. ADVANCES AND TRENDS IN ARTIFICIAL INTELLIGENCE: FROM THEORY TO PRACTICE, 2019, 11606 : 89 - 101