DocumentCode :
3707618
Title :
Improving deep convolutional neural networks with unsupervised feature learning
Author :
Kien Nguyen;Clinton Fookes;Sridha Sridharan
Author_Institution :
Image and Video lab, SAIVT Research Program, Queensland University of Technology, Brisbane, Australia
fYear :
2015
Firstpage :
2270
Lastpage :
2274
Abstract :
The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.
Keywords :
"Training","Machine learning","Computer architecture","Unsupervised learning","Neural networks","Supervised learning","Convolutional codes"
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2015 IEEE International Conference on
Type :
conf
DOI :
10.1109/ICIP.2015.7351206
Filename :
7351206
Link To Document :
بازگشت