Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network

被引:4
|
作者
Oki, Hideki [1 ]
Kurita, Takio [1 ]
机构
[1] Hiroshima Univ, Grad Sch Engn, Dept Informat Engn, Higashihiroshima, Japan
关键词
D O I
10.1007/978-3-030-04179-3_56
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The deep Convolutional Neural Network (CNN) became very popular as a fundamental technique for image classification and objects recognition. To improve the recognition accuracy for the more complex tasks, deeper networks have being introduced. However, the recognition accuracy of the trained deep CNN drastically decreases for the samples which are obtained from the outside regions of the training samples. To improve the generalization ability for such samples, Krizhevsky et al. proposed to generate additional samples through transformations from the existing samples and to make the training samples richer. This method is known as data augmentation. Hongyi Zhang et al. introduced data augmentation method called mixup which achieves state-of-the-art performance in various datasets. Mixup generates new samples by mixing two different training samples. Mixing of the two images is implemented with simple image morphing. In this paper, we propose to apply mixup to the feature maps in a hidden layer. To implement the mixup in the hidden layer we use the Siamese network or the triplet network architecture to mix feature maps. From the experimental comparison, it is observed that the mixup of the feature maps obtained from the first convolution layer is more effective than the original image mixup.
引用
收藏
页码:635 / 644
页数:10
相关论文
共 50 条
  • [31] Wide Hidden Expansion Layer for Deep Convolutional Neural Networks
    Wang, Min
    Liu, Baoyuan
    Foroosh, Hassan
    [J]. 2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 923 - 931
  • [32] EEG-based Emotion Recognition Under Convolutional Neural Network with Differential Entropy Feature Maps
    Li, Yifan
    Wong, Chi Man
    Zheng, Yudian
    Wan, Feng
    Mak, Peng Un
    Pun, Sio Hang
    Vai, Mang, I
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND VIRTUAL ENVIRONMENTS FOR MEASUREMENT SYSTEMS AND APPLICATIONS (CIVEMSA 2019), 2019, : 6 - 10
  • [33] Classification for Breast Ultrasound Using Convolutional Neural Network with Multiple Time-Domain Feature Maps
    Kim, Hyungsuk
    Park, Juyoung
    Lee, Hakjoon
    Im, Geuntae
    Lee, Jongsoo
    Lee, Ki-Baek
    Lee, Heung Jae
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (21):
  • [34] The hidden layer design of the MVQ neural network
    Abouali, AH
    Porter, WA
    [J]. THIRTIETH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY (SSST), 1998, : 393 - 396
  • [35] A hierarchical training-convolutional neural network with feature alignment for steel surface defect recognition
    Gao, Yiping
    Gao, Liang
    Li, Xinyu
    [J]. ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2023, 81
  • [36] Dynamic sparsity and model feature learning enhanced training for convolutional neural network-pruning
    Ruan X.
    Hu W.
    Liu Y.
    Li B.
    [J]. Zhongguo Kexue Jishu Kexue/Scientia Sinica Technologica, 2022, 52 (05): : 667 - 681
  • [37] Hyperspectral images classification with convolutional neural network and textural feature using limited training samples
    Zhao, Wudi
    Li, Shanshan
    Li, An
    Zhang, Bing
    Li, Yu
    [J]. REMOTE SENSING LETTERS, 2019, 10 (05) : 449 - 458
  • [38] A novel training algorithm for convolutional neural network
    Anuse, Alwin
    Vyas, Vibha
    [J]. COMPLEX & INTELLIGENT SYSTEMS, 2016, 2 (03) : 221 - 234
  • [39] A double-layer feature fusion convolutional neural network for infrared small target detection
    Li, Dandan
    Pang, Boyu
    Lv, Shuai
    Yin, Zhonghai
    Lian, Xiaoying
    Sun, Dexin
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (02) : 407 - 427
  • [40] Auxiliary Structure for Convolutional Neural Network Training
    Chen, Cheng-Yeh
    Chiang, Chen-Kuo
    [J]. 2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 1995 - 1999