Local Binary Convolutional Neural Networks

被引:150
|
作者
Juefei-Xu, Felix [1 ]
Boddeti, Vishnu Naresh [2 ]
Savvides, Marios [1 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[2] Michigan State Univ, E Lansing, MI 48824 USA
来源
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年
关键词
D O I
10.1109/CVPR.2017.456
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose local binary convolution (LBC), an efficient alternative to convolutional layers in standard convolutional neural networks (CNN). The design principles of LBC are motivated by local binary patterns (LBP). The LBC layer comprises of a set of fixed sparse pre-defined binary convolutional filters that are not updated during the training process, a non-linear activation function and a set of learnable linear weights. The linear weights combine the activated filter responses to approximate the corresponding activated filter responses of a standard convolutional layer. The LBC layer affords significant parameter savings, 9x to 169x in the number of learnable parameters compared to a standard convolutional layer. Furthermore, the sparse and binary nature of the weights also results in up to 9x to 169x savings in model size compared to a standard convolutional layer. We demonstrate both theoretically and experimentally that our local binary convolution layer is a good approximation of a standard convolutional layer. Empirically, CNNs with LBC layers, called local binary convolutional neural networks (LBCNN), achieves performance parity with regular CNNs on a range of visual datasets (MNIST, SVHN, CIFAR-10, and ImageNet) while enjoying significant computational savings.
引用
收藏
页码:4284 / 4293
页数:10
相关论文
共 50 条
  • [1] GRADIENT LOCAL BINARY PATTERN FOR CONVOLUTIONAL NEURAL NETWORKS
    Tang, Jialiang
    Jiang, Ning
    Yu, Wenxin
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 744 - 748
  • [2] Masked face recognition with convolutional neural networks and local binary patterns
    Vu, Hoai Nam
    Nguyen, Mai Huong
    Pham, Cuong
    APPLIED INTELLIGENCE, 2022, 52 (05) : 5497 - 5512
  • [3] Using Local Binary Patterns and Convolutional Neural Networks for Melanoma Detection
    Iqbal, Saeed
    Qureshi, Adnan N.
    Akter, Mukti
    INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 2, 2020, 1038 : 782 - 789
  • [4] Convolutional neural networks and local binary patterns for hyperspectral image classification
    Wei, Xiangpo
    Yu, Xuchu
    Liu, Bing
    Zhi, Lu
    EUROPEAN JOURNAL OF REMOTE SENSING, 2019, 52 (01) : 448 - 462
  • [5] Masked face recognition with convolutional neural networks and local binary patterns
    Hoai Nam Vu
    Mai Huong Nguyen
    Cuong Pham
    Applied Intelligence, 2022, 52 : 5497 - 5512
  • [6] Gradient Local Binary Pattern Layer to Initialize the Convolutional Neural Networks
    Jiang, Ning
    Tang, Jialiang
    Yu, Wenxin
    Zhou, Jinjia
    Mai, Liuwei
    2021 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2021,
  • [7] Exploring the Limitations of the Convolutional Neural Networks on Binary Tests Selection for Local Features
    Goncalves Biesseck, Bernardo Janko
    Araujo Junior, Edson Araujo
    Nascimento, Erickson R.
    VISAPP: PROCEEDINGS OF THE 14TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4, 2019, : 261 - 271
  • [8] Deterministic Binary Filters for Convolutional Neural Networks
    Tseng, Vincent W-S
    Bhattachara, Sourav
    Fernandez-Marques, Javier
    Alizadeh, Milad
    Tong, Catherine
    Lane, Nicholas D.
    PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 2739 - 2747
  • [9] GABOR BINARY LAYER IN CONVOLUTIONAL NEURAL NETWORKS
    Jiang, Chenzhi
    Su, Jianbo
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 3408 - 3412
  • [10] One dimensional convolutional neural networks and local binary patterns for hyperspectral image classification
    Miclea, Andreia Valentina
    Terebes, Romulus
    Meza, Serban
    PROCEEDINGS OF 2020 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION, QUALITY AND TESTING, ROBOTICS (AQTR), 2020, : 373 - 378