X. Zhang, L. Liu, Y. Xie, J. Chen, L. Wu and M. Pietikäinen, "Rotation Invariant Local Binary Convolution Neural Networks," 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, 2017, pp. 1210-1219. doi: 10.1109/ICCVW.2017.146
Rotation invariant local binary convolution neural networks
|Author:||Zhang, Xin1; Liu, Li1,2; Xie, Yuxiang1;|
11College of Information System and Management, National University of Defense Technology, China
2CMVS, University of Oulu, Finland
3The Key Laboratory, Academy of Equipment, Beijing, China
|Online Access:||PDF Full Text (PDF, 0.5 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe202003057306
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2020-03-05
Although Convolution Neural Networks(CNNs) are unprecedentedly powerful to learn effective representations, they are still parameter expensive and limited by the lack of ability to handle with the orientation transformation of the input data. To alleviate this problem, we propose a deep architecture named Rotation Invariant Local Binary Convolution Neural Network(RI-LBCNN). RI-LBCNN is a deep convolution neural network consisting of Local Binary orientation Module(LBoM). A LBoM is composed of two parts, i.e., three layers steerable module (two layers for the first and one for the second part), which is a combination of Local Binary Convolution (LBC) and Active Rotating Filters (ARFs). Through replacing the basic convolution layer in DCNN with LBoMs, RI-LBCNN can be easily implemented and LBoM can be naturally inserted to other popular models without any extra modification to the optimisation process. Meanwhile, the proposed RI-LBCNN thus can be easily trained end to end. Extensive experiments show that the updating with the proposed LBoMs leads to significant reduction of learnable parameters and the reasonable performance improvement on three benchmarks.
|Pages:||1210 - 1219|
2017 IEEE International Conference on Computer Vision Workshop (ICCVW)
IEEE International Conference on Computer Vision Workshops
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
This work is funded by the National Natural Science Foundation of China(61571453, 61202336), the Natural Science Foundation of Hunan Province(14JJ3010) and the Hunan Provincial Natural Science Fund for Distinguished Young Scholars(2017JJ1007). Tekes, Academy of Finland and Infotech Oulu are also gratefully acknowledged.
© 2017 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.