IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v11y2019i1p9-d194475.html
   My bibliography  Save this article

Object Detection Network Based on Feature Fusion and Attention Mechanism

Author

Listed:
  • Ying Zhang

    (School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China)

  • Yimin Chen

    (School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
    Shanghai Institute for Advanced Communication and Data Science, Shanghai 200444, China)

  • Chen Huang

    (School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China)

  • Mingke Gao

    (The 32nd Research Institute, China Electronics Technology Group Corporation, No. 63 Chengliugong Road, Jiading District, Shanghai 200444, China)

Abstract

In recent years, almost all of the current top-performing object detection networks use CNN (convolutional neural networks) features. State-of-the-art object detection networks depend on CNN features. In this work, we add feature fusion in the object detection network to obtain a better CNN feature, which incorporates well deep, but semantic, and shallow, but high-resolution, CNN features, thus improving the performance of a small object. Also, the attention mechanism was applied to our object detection network, AF R-CNN (attention mechanism and convolution feature fusion based object detection), to enhance the impact of significant features and weaken background interference. Our AF R-CNN is a single end to end network. We choose the pre-trained network, VGG-16, to extract CNN features. Our detection network is trained on the dataset, PASCAL VOC 2007 and 2012. Empirical evaluation of the PASCAL VOC 2007 dataset demonstrates the effectiveness and improvement of our approach. Our AF R-CNN achieves an object detection accuracy of 75.9% on PASCAL VOC 2007, six points higher than Faster R-CNN.

Suggested Citation

  • Ying Zhang & Yimin Chen & Chen Huang & Mingke Gao, 2019. "Object Detection Network Based on Feature Fusion and Attention Mechanism," Future Internet, MDPI, vol. 11(1), pages 1-14, January.
    • Handle: RePEc:gam:jftint:v:11:y:2019:i:1:p:9-:d:194475
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/11/1/9/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1999-5903/11/1/9/
    Download Restriction: no
    ---><---

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    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. Dimitris Ziouzios & Dimitris Tsiktsiris & Nikolaos Baras & Minas Dasygenis, 2020. "A Distributed Architecture for Smart Recycling Using Machine Learning," Future Internet, MDPI, vol. 12(9), pages 1-13, August.

    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:11:y:2019:i:1:p:9-:d:194475. 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.

    We have no bibliographic references for this item. You can help adding them by using 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.