Supervised two-step hash learning for efficient image retrieval

Xinhui Wu, Sei Ichiro Kamata, Lizhuang Ma

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ190-195
ページ数6
ISBN(電子版)9781538633540
DOI
出版ステータスPublished - 2018 12 13
イベント4th Asian Conference on Pattern Recognition, ACPR 2017 - Nanjing, China
継続期間: 2017 11 262017 11 29

出版物シリーズ

名前Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017

Other

Other4th Asian Conference on Pattern Recognition, ACPR 2017
CountryChina
CityNanjing
Period17/11/2617/11/29

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

フィンガープリント 「Supervised two-step hash learning for efficient image retrieval」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル