Unsupervised deep hashing for large-scale visual search

Xia, Zhaoqiang; Feng, Xiaoyi; Peng, Jinye; Hadid, Abdenour (2017-01-19)
 
Avaa tiedosto
Lataukset: 

URL:
https://doi.org/10.1109/IPTA.2016.7821007

Xia, Zhaoqiang
Feng, Xiaoyi
Peng, Jinye
Hadid, Abdenour
Institute of Electrical and Electronics Engineers
19.01.2017

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

https://rightsstatements.org/vocab/InC/1.0/
© 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.
https://rightsstatements.org/vocab/InC/1.0/
doi:https://doi.org/10.1109/IPTA.2016.7821007
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2019060618853
Tiivistelmä

Abstract

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.

Kokoelmat