Orientation and scale based weights initialization scheme for deep convolutional neural networks
Image classification is generally about the understanding of information in the images concerned. The more the system able to understand the image contains, the more effective it will be in classifying desired images. Recent work has shown that the convolutional neural network (CNN) paradigm is...
Saved in:
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Penerbit Universiti Kebangsaan Malaysia
2020
|
Online Access: | http://journalarticle.ukm.my/16839/1/08.pdf http://journalarticle.ukm.my/16839/ https://www.ukm.my/apjitm/articles-year.php |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Image classification is generally about the understanding of information in the images concerned. The more the
system able to understand the image contains, the more effective it will be in classifying desired images. Recent
work has shown that the convolutional neural network (CNN) paradigm is useful for obtaining more accurate
image classification results. A crucial component in the CNN is the convolution filters which consist of a series
of predefined filter weight initialization values. The filter weights are then automatically learned by the neural
network throughout the back- propagation training algorithm. However, most initialization schemes used in the
deep convolutional neural networks are mainly to deal with vanishing gradient problems. Thus, selecting optimal
weights are crucial to improve convergence and minimize the complexity which can enhance the generalization
performance. One possible solution is to replace the standard weights with parameterized filters that proven to be
efficient in extracting useful features such as Gabor filter bank. The Gabor filter bank is popular due to its ability
in dealing with spatial transformation, especially on edges and texture information of different scales and
directions. Thus, in this paper, we investigate the effect of utilizing Gabor and convolutional filters on small size
kernels of deep VGG-16 architecture. The standard VGG-16 filter is replaced with the Gabor filter bank to obtain
uniform distribution at all layers of the network. The result shows that the orientation and scale weights
initialization scheme outperforms the standard filter weights on an image classification problem. |
---|