University of Oulu

X. Zhang, Y. Xie, J. Chen, L. Wu, Q. Ye and L. Liu, "Rotation Invariant Local Binary Convolution Neural Networks," in IEEE Access, vol. 6, pp. 18420-18430, 2018. doi: 10.1109/ACCESS.2018.2818887

Rotation invariant local binary convolution neural networks

Saved in:
Author: Zhang, Xin1; Xie, Yuxiang1; Chen, Jie2;
Organizations: 1College of Information System and Management, National University of Defense Technology, Changsha, China
2Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
3Space Engineering University, Beijing, China
4University of Chinese Academy of Sciences, Beijing, China
Format: article
Version: published version
Access: open
Persistent link: http://urn.fi/urn:nbn:fi-fe2018061125687
Language: English
Published: Institute of Electrical and Electronics Engineers, 2018
Publish Date: 2018-06-11
Description:

Abstract

Convolutional neural networks (CNNs) have achieved unprecedented successes in computer vision fields, but they remain challenged by the problem about how to effectively process the orientation transformation of objects with fewer parameters. In this paper, we propose a new convolutional module, local binary orientation module (LBoM), which takes advantages of both local binary convolutional and active rotating filters to effectively deal with the rotation variations with fewer parameters. LBoM can be naturally inserted to popular CNN models and upgrade them to be rotation invariant local binary CNNs (RI-LBCNNs). RI-LBCNNs can be learned with off-the-shelf optimization approaches in an end-to-end manner and fulfill image classification tasks. Extensive experiments on four benchmarks show that RI-LBCNNs can perform image classification with fewer network parameters and significantly outperform the baseline LBCNN when processing images with large rotation variations.

see all

Series: IEEE access
ISSN: 2169-3536
ISSN-E: 2169-3536
ISSN-L: 2169-3536
Volume: 6
Pages: 18420 - 18430
DOI: 10.1109/ACCESS.2018.2818887
OADOI: https://oadoi.org/10.1109/ACCESS.2018.2818887
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Subjects:
Funding: Tekes, Academy of Finland and Infotech Oulu are also gratefully acknowledged.
Copyright information: © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.