TY - GEN
T1 - Supervised two-step hash learning for efficient image retrieval
AU - Wu, Xinhui
AU - Kamata, Sei Ichiro
AU - Ma, Lizhuang
N1 - Funding Information:
This work was partially supported by JSPS KAK-ENHI Grant Number 15K00248 and fund of Shanghai Science and Technology Commission Grant Number 16511101300.
Publisher Copyright:
© 2017 IEEE.
PY - 2018/12/13
Y1 - 2018/12/13
N2 - Content-based image retrieval (CBIR) attracts more and more interests in modern applications. Hashing method is a popular solution of CBIR. Among all the hashing methods, supervised deep learning approaches have received brilliant advantages encouraged by the rapid development of convolutional neural networks in recent years. In this paper, we propose a supervised two-step hash learning method that demonstrates high accuracy and fast speed. Our technical contributions include a feature preparation part and a two-step hash learning process with a carefully designed prototype code system for utilizing supervised labels. Our method achieves satisfactory results via a quite short training time. We can extract well similarity-preserving features, learn a comprehensive function mapping and get compact hash codes as well. Experiments are conducted on some widely-used public benchmarks MNIST and CIFAR-10, indicating that our proposed method outperforms several state-of-The-Art methods by significant improvement.
AB - Content-based image retrieval (CBIR) attracts more and more interests in modern applications. Hashing method is a popular solution of CBIR. Among all the hashing methods, supervised deep learning approaches have received brilliant advantages encouraged by the rapid development of convolutional neural networks in recent years. In this paper, we propose a supervised two-step hash learning method that demonstrates high accuracy and fast speed. Our technical contributions include a feature preparation part and a two-step hash learning process with a carefully designed prototype code system for utilizing supervised labels. Our method achieves satisfactory results via a quite short training time. We can extract well similarity-preserving features, learn a comprehensive function mapping and get compact hash codes as well. Experiments are conducted on some widely-used public benchmarks MNIST and CIFAR-10, indicating that our proposed method outperforms several state-of-The-Art methods by significant improvement.
KW - hash learning
KW - image retrieval
KW - prototype code
UR - http://www.scopus.com/inward/record.url?scp=85059037615&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059037615&partnerID=8YFLogxK
U2 - 10.1109/ACPR.2017.83
DO - 10.1109/ACPR.2017.83
M3 - Conference contribution
AN - SCOPUS:85059037615
T3 - Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017
SP - 190
EP - 195
BT - Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th Asian Conference on Pattern Recognition, ACPR 2017
Y2 - 26 November 2017 through 29 November 2017
ER -