Z. Xia, X. Feng, J. Peng and A. Hadid, "Unsupervised deep hashing for large-scale visual search," 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), Oulu, 2016, pp. 1-5. doi: 10.1109/IPTA.2016.7821007
Unsupervised deep hashing for large-scale visual search
|Author:||Xia, Zhaoqiang1; Feng, Xiaoyi1; Peng, Jinye1;|
1School of Electronics and Information, Northwestern Polytechnical University
2Center for Machine Vision Research, University of Oulu
|Online Access:||PDF Full Text (PDF, 0.2 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2019060618853
Institute of Electrical and Electronic Engineers,
|Publish Date:|| 2019-06-06
Learning based hashing plays a pivotal role in large-scale visual search. However, most existing hashing algorithms tend to learn shallow models that do not seek representative binary codes. In this paper, we propose a novel hashing approach based on unsupervised deep learning to hierarchically transform features into hash codes. Within the heterogeneous deep hashing framework, the autoencoder layers with specific constraints are considered to model the nonlinear mapping between features and binary codes. Then, a Restricted Boltzmann Machine (RBM) layer with constraints is utilized to reduce the dimension in the hamming space. The experiments on the problem of visual search demonstrate the competitiveness of our proposed approach compared to the state of the art.
Proceedings. International Workshops on Image Processing Theory, Tools, and Applications
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), 12 - 15 Dec 2016 Oulu, Finland
|Host publication editor:||
Bordallo López, Miguel
International Conference on Image Processing Theory, Tools and Applications
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
222 Other engineering and technologies
This work is partly supported by the Fundamental Research Funds of Northwestern Polytechnical University (NO.G2015KY0302).
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.