Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 190-195 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781538633540 |
| DOIs | |
| Publication status | Published - 2018 Dec 13 |
| Event | 4th Asian Conference on Pattern Recognition, ACPR 2017 - Nanjing, China Duration: 2017 Nov 26 → 2017 Nov 29 |
Other
| Other | 4th Asian Conference on Pattern Recognition, ACPR 2017 |
|---|---|
| Country | China |
| City | Nanjing |
| Period | 17/11/26 → 17/11/29 |
Fingerprint
Keywords
- hash learning
- image retrieval
- prototype code
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
Supervised two-step hash learning for efficient image retrieval. / Wu, Xinhui; Kamata, Seiichiro; Ma, Lizhuang.
Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 190-195 8575821.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Supervised two-step hash learning for efficient image retrieval
AU - Wu, Xinhui
AU - Kamata, Seiichiro
AU - Ma, Lizhuang
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
SP - 190
EP - 195
BT - Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -