Faster method for Deep Belief Network based Object classification using DWT

2015/11/19 by Saurabh Sihag, Sihag, Saurabh, Pranab Kumar Dutta +1
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1511.06276

arxiv created 2015/11/19 · arxiv updated 2015/11/20

Abstract

A Deep Belief Network (DBN) requires large, multiple hidden layers with high number of hidden units to learn good features from the raw pixels of large images. This implies more training time as well as computational complexity. By integrating DBN with Discrete Wavelet Transform (DWT), both training time and computational complexity can be reduced. The low resolution images obtained after application of DWT are used to train multiple DBNs. The results obtained from these DBNs are combined using a weighted voting algorithm. The performance of this method is found to be competent and faster in comparison with that of traditional DBNs.

Related

• A brief survey on deep belief networks and introducing a new object oriented toolbox (DeeBNet)
• Behavior and performance of the deep belief networks on image classification
• An Object Detection by using Adaptive Structural Learning of Deep Belief Network
• Distinction between features extracted using deep belief networks
• Deep Adversarial Belief Networks