Open Access
ARTICLE
IDSH: An Improved Deep Supervised Hashing Method for Image Retrieval
Chaowen Lu1,a, Feifei Lee1,a,*, Lei Chen1, Sheng Huang1, Qiu Chen2,*
1 School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China.
2 Major of Electrical Engineering and Electronics, Graduate School of Engineering, Kogakuin University, 1-24-2, Nishi-shinjuku, Sinjuku-ku, Tokyo, 163-8677, Japan.
a Both authors contributed equally to this work.
∗ Corresponding Authors: Feifei Lee. Email: ;
Qiu Chen. Email: .
Computer Modeling in Engineering & Sciences 2019, 121(2), 593-608. https://doi.org/10.32604/cmes.2019.07796
Abstract
Image retrieval has become more and more important because of the explosive
growth of images on the Internet. Traditional image retrieval methods have limited image
retrieval performance due to the poor image expression abhility of visual feature and
high dimension of feature. Hashing is a widely-used method for Approximate Nearest
Neighbor (ANN) search due to its rapidity and timeliness. Meanwhile, Convolutional
Neural Networks (CNNs) have strong discriminative characteristics which are used for
image classification. In this paper, we propose a CNN architecture based on improved
deep supervised hashing (IDSH) method, by which the binary compact codes can be
generated directly. The main contributions of this paper are as follows: first, we add a
Batch Normalization (BN) layer before each activation layer to prevent the gradient from
vanishing and improve the training speed; secondly, we use Divide-and-Encode Module to
map image features to approximate hash codes; finally, we adopt center loss to optimize
training. Extensive experimental results on four large-scale datasets: MNIST, CIFAR-10,
NUS-WIDE and SVHN demonstrate the effectiveness of the proposed method compared
with other state-of-the-art hashing methods.
Keywords
Cite This Article
Lu, C., Lee, F., Chen, L., Huang, S., Chen, Q. (2019). IDSH: An Improved Deep Supervised Hashing Method for Image Retrieval.
CMES-Computer Modeling in Engineering & Sciences, 121(2), 593–608.
Citations