IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v12y2020i11p178-d432866.html
   My bibliography  Save this article

Learning a Hierarchical Global Attention for Image Classification

Author

Listed:
  • Kerang Cao

    (Shenyang University of Chemical Technology, Shenyang 110000, China)

  • Jingyu Gao

    (Shenyang University of Chemical Technology, Shenyang 110000, China)

  • Kwang-nam Choi

    (NTIS Center, Korea Institute of Science and Technology Information, Seoul 02792, Korea)

  • Lini Duan

    (Shenyang University of Chemical Technology, Shenyang 110000, China)

Abstract

To classify the image material on the internet, the deep learning methodology, especially deep neural network, is the most optimal and costliest method of all computer vision methods. Convolutional neural networks (CNNs) learn a comprehensive feature representation by exploiting local information with a fixed receptive field, demonstrating distinguished capacities on image classification. Recent works concentrate on efficient feature exploration, which neglect the global information for holistic consideration. There is large effort to reduce the computational costs of deep neural networks. Here, we provide a hierarchical global attention mechanism that improve the network representation with restricted increase of computation complexity. Different from nonlocal-based methods, the hierarchical global attention mechanism requires no matrix multiplication and can be flexibly applied in various modern network designs. Experimental results demonstrate that proposed hierarchical global attention mechanism can conspicuously improve the image classification precision—a reduction of 7.94% and 16.63% percent in Top 1 and Top 5 errors separately—with little increase of computation complexity (6.23%) in comparison to competing approaches.

Suggested Citation

  • Kerang Cao & Jingyu Gao & Kwang-nam Choi & Lini Duan, 2020. "Learning a Hierarchical Global Attention for Image Classification," Future Internet, MDPI, vol. 12(11), pages 1-11, October.
  • Handle: RePEc:gam:jftint:v:12:y:2020:i:11:p:178-:d:432866
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/12/11/178/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1999-5903/12/11/178/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Anping Song & Zuoyu Wu & Xuehai Ding & Qian Hu & Xinyi Di, 2018. "Neurologist Standard Classification of Facial Nerve Paralysis with Deep Neural Networks," Future Internet, MDPI, vol. 10(11), pages 1-13, November.
    2. Xiangpeng Song & Hongbin Yang & Congcong Zhou, 2019. "Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios," Future Internet, MDPI, vol. 11(11), pages 1-13, November.
    3. George Albert Florea & Radu-Casian Mihailescu, 2020. "Multimodal Deep Learning for Group Activity Recognition in Smart Office Environments," Future Internet, MDPI, vol. 12(8), pages 1-13, August.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Salvatore Graziani & Maria Gabriella Xibilia, 2020. "Innovative Topologies and Algorithms for Neural Networks," Future Internet, MDPI, vol. 12(7), pages 1-4, July.
    2. Chuanyan Hao & Anqi Zheng & Yuqi Wang & Bo Jiang, 2021. "Experiment Information System Based on an Online Virtual Laboratory," Future Internet, MDPI, vol. 13(2), pages 1-19, January.
    3. Jie Yu & Yaliu Li & Chenle Pan & Junwei Wang, 2021. "A Classification Method for Academic Resources Based on a Graph Attention Network," Future Internet, MDPI, vol. 13(3), pages 1-16, March.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jftint:v:12:y:2020:i:11:p:178-:d:432866. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.