most citedDCT Perceptron Layer: A Transform Domain Approach for Convolution Layer

5 citations · 12 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV20225 cited

DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer

Hongyi Pan, Xin Zhu, Salih Atici +1

In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the Conv2D layers in the Residual ne…

eess.IV2022

Classification of the Cervical Vertebrae Maturation (CVM) stages Using the Tripod Network

Salih Atici, Hongyi Pan, Mohammed H. Elnagar +4

We present a novel deep learning method for fully automated detection and classification of the Cervical Vertebrae Maturation (CVM) stages. The deep convolutional neural network co…

cs.CV20223 cited

Multipod Convolutional Network

Hongyi Pan, Salih Atici, Ahmet Enis Cetin

In this paper, we introduce a convolutional network which we call MultiPodNet consisting of a combination of two or more convolutional networks which process the input image in par…

cs.LG20223 cited

Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks

Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin

Convolution has been the core operation of modern deep neural networks. It is well-known that convolutions can be implemented in the Fourier Transform domain. In this paper, we pro…

cs.LG20211 cited

Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm

Hongyi Pan, Diaa Badawi, Erdem Koyuncu +1

We consider a family of vector dot products that can be implemented using sign changes and addition operations only. The dot products are energy-efficient as they avoid the multipl…

cs.CV2021

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

Hongyi Pan, Diaa Dabawi, Ahmet Enis Cetin

In this paper, we propose a novel layer based on fast Walsh-Hadamard transform (WHT) and smooth-thresholding to replace convolution layers in deep neural networks. In t…