Browsing Waterloo Research by Subject "convolution neural network"

Now showing items 1-3 of 3

Global-connected network with generalized ReLU activation

Chen, Zhi; Ho, Pin-Han (Elsevier, 2019-12)

Recent Progress has shown that exploitation of hidden layer neurons in convolutional neural networks (CNN) incorporating with a carefully designed activation function can yield better classification results in the field ...
Learning Filters for the 2D Wavelet Transform

Recoskie, Daniel; Mann, Richard (IEEE, 2018)

We propose a new method for learning filters for the 2D discrete wavelet transform. We extend our previous work on the 1D wavelet transform in order to process images. We show that the 2D wavelet transform can be represented ...
Stereoscopic image quality assessment by deep convolutional neural network

Fang, Yuming; Yan, Jiebin; Liu, Xuelin; Wang, Jiheng (Elsevier, 2019-01)

In this paper, we propose a no-reference (NR) quality assessment method for stereoscopic images by deep convolutional neural network (DCNN). Inspired by the internal generative mechanism (IGM) in the human brain, which ...