中国邮电高校学报(英文) ›› 2019, Vol. 26 ›› Issue (4): 51-61.doi: DOI: 10.19682/j.cnki.1005-8885.2019.1017

• Artificial Intelligence • 上一篇    下一篇

Supervised learning of enhancing convolutional Hash for image retrieval

Zhai Qi, Jiang Mingyan   

  1. School of Information Science and Engineering, Shandong University, Qingdao 266237, China
  • 收稿日期:2018-06-05 修回日期:2019-08-16 出版日期:2019-08-31 发布日期:2019-10-29
  • 通讯作者: Corresponding author: Jiang Mingyan, E-mail: jiangmingyan@sdu.edu.cn E-mail:jiangmingyan@sdu.edu.cn
  • 作者简介:Corresponding author: Jiang Mingyan, E-mail: jiangmingyan@sdu.edu.cn
  • 基金资助:
    This work was supported by the Natural Science Foundation of Shandong Province (ZR2014FM039) and the National Natural Science Foundation of China (61771293).

Supervised learning of enhancing convolutional Hash for image retrieval

Zhai Qi, Jiang Mingyan   

  1. School of Information Science and Engineering, Shandong University, Qingdao 266237, China
  • Received:2018-06-05 Revised:2019-08-16 Online:2019-08-31 Published:2019-10-29
  • Contact: Corresponding author: Jiang Mingyan, E-mail: jiangmingyan@sdu.edu.cn E-mail:jiangmingyan@sdu.edu.cn
  • About author:Corresponding author: Jiang Mingyan, E-mail: jiangmingyan@sdu.edu.cn
  • Supported by:
    This work was supported by the Natural Science Foundation of
    Shandong Province (ZR2014FM039) and the National Natural
    Science Foundation of China (61771293).

摘要: Deep convolutional neural network (CNN) makes great breakthroughs in computer vision. Recently, many works have demonstrated that the performance of the CNN depends on the stacked convolutional layers. It is obvious that the features of the fully connected layers lose the topological structures of images, and the convolutional layer features contain a large amount of redundant information that interferes with the performance of model. Thus, we propose an effective supervised deep Hashing method, enhancing convolutional deep Hashing (ECDH), which learns the binary codes from the strengthened convolutional layer. Specifically, an enhanced convolutional Hash layer is constructed between the top convolutional layer and the output layer, enhancing the local features of the convolutional layer outputs while learning the binary codes by optimizing an objective function. The proposed method works well for existing deep learning models such as Alex neural network (AlexNet), visual geometry group neural network (VGGNet), residual neural network (ResNet), and is easier to be trained. Compared with state-of-the-art methods, extensive experiments show that the proposed method achieves better retrieval performance.

关键词: CNN, Hashing, image retrieval, Hamming distance

Abstract: Deep convolutional neural network (CNN) makes great breakthroughs in computer vision. Recently, many works have demonstrated that the performance of the CNN depends on the stacked convolutional layers. It is obvious that the features of the fully connected layers lose the topological structures of images, and the convolutional layer features contain a large amount of redundant information that interferes with the performance of model. Thus, we propose an effective supervised deep Hashing method, enhancing convolutional deep Hashing (ECDH), which learns the binary codes from the strengthened convolutional layer. Specifically, an enhanced convolutional Hash layer is constructed between the top convolutional layer and the output layer, enhancing the local features of the convolutional layer outputs while learning the binary codes by optimizing an objective function. The proposed method works well for existing deep learning models such as Alex neural network (AlexNet), visual geometry group neural network (VGGNet), residual neural network (ResNet), and is easier to be trained. Compared with state-of-the-art methods, extensive experiments show that the proposed method achieves better retrieval performance.

Key words: CNN, Hashing, image retrieval, Hamming distance

中图分类号: