no code implementations • 10 May 2024 • Debesh Jha, Nikhil Kumar Tomar, Koushik Biswas, Gorkem Durak, Matthew Antalek, Zheyuan Zhang, Bin Wang, Md Mostafijur Rahman, Hongyi Pan, Alpay Medetalibeyoglu, Yury Velichko, Daniela Ladner, Amir Borhani, Ulas Bagci
Each decoder network is connected to a different part of the encoder via a multi-scale feature enhancement dilated block.
no code implementations • 2 May 2024 • Abhijit Das, Debesh Jha, Vandan Gorade, Koushik Biswas, Hongyi Pan, Zheyuan Zhang, Daniela P. Ladner, Yury Velichko, Amir Borhani, Ulas Bagci
Computer-aided segmentation methods can assist medical personnel in improving diagnostic outcomes.
no code implementations • 8 Mar 2024 • Xin Zhu, Hongyi Pan, Yury Velichko, Adam B. Murphy, Ashley Ross, Baris Turkbey, Ahmet Enis Cetin, Ulas Bagci
Random samples drawn from latent space are then incorporated with a prototypical corrected image to generate multiple plausible images.
no code implementations • 4 Oct 2023 • Xin Zhu, Daoguang Yang, Hongyi Pan, Hamid Reza Karimi, Didem Ozevin, Ahmet Enis Cetin
In comparison to the linear layer, the DCST layer reduces the number of trainable parameters and improves the accuracy of data reconstruction.
1 code implementation • 18 Sep 2023 • Hongyi Pan, Bin Wang, Zheyuan Zhang, Xin Zhu, Debesh Jha, Ahmet Enis Cetin, Concetto Spampinato, Ulas Bagci
However, it neglects background interference in the amplitude spectrum.
no code implementations • 15 Sep 2023 • Xin Zhu, Hongyi Pan, Salih Atici, Ahmet Enis Cetin
Traditional preamble detection algorithms have low accuracy in the grant-based random access scheme in massive machine-type communication (mMTC).
no code implementations • 15 Sep 2023 • Xin Zhu, Hongyi Pan, Shuaiang Rong, Ahmet Enis Cetin
The latent space data is transmitted to the receiver.
no code implementations • 4 Sep 2023 • Nastaran Darabi, Maeesha Binte Hashem, Hongyi Pan, Ahmet Cetin, Wilfred Gomes, Amit Ranjan Trivedi
Moreover, our novel array micro-architecture enables adaptive stitching of cells column-wise and row-wise, thereby facilitating perfect parallelism in computations.
no code implementations • 21 Jun 2023 • Ziliang Hong, Emadeldeen Hamdan, Yifei Zhao, Tianxiao Ye, Hongyi Pan, A. Enis Cetin
This paper surveys different publicly available neural network models used for detecting wildfires using regular visible-range cameras which are placed on hilltops or forest lookout towers.
1 code implementation • 29 May 2023 • Bin Wang, Hongyi Pan, Armstrong Aboah, Zheyuan Zhang, Elif Keles, Drew Torigian, Baris Turkbey, Elizabeth Krupinski, Jayaram Udupa, Ulas Bagci
To our best knowledge, GazeGNN is the first work that adopts GNN to integrate image and eye-gaze data.
1 code implementation • 27 May 2023 • Hongyi Pan, Xin Zhu, Salih Atici, Ahmet Enis Cetin
In this paper, we propose a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing.
1 code implementation • 13 Mar 2023 • Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Salih Atici, Ahmet Enis Cetin
Trainable soft-thresholding layers, that remove noise in the transform domain, bring nonlinearity to the transform domain layers.
1 code implementation • 20 Dec 2022 • Salih Atici, Hongyi Pan, Ahmet Enis Cetin
We evaluate the efficiency of our training algorithm on benchmark datasets using ResNet-18, WResNet-20, ResNet-50, and a toy neural network.
1 code implementation • 15 Nov 2022 • Hongyi Pan, Xin Zhu, Zhilu Ye, Pai-Yen Chen, Ahmet Enis Cetin
To improve the estimation precision, we propose a neural network that uses a novel Discrete Cosine Transform (DCT) layer to denoise and decorrelates the data.
no code implementations • 15 Nov 2022 • Hongyi Pan, Xin Zhu, Salih Atici, Ahmet Enis Cetin
In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the $3\times3$ Conv2D layers in the Residual neural Network (ResNet).
no code implementations • 15 Nov 2022 • Salih Atici, Hongyi Pan, Mohammed H. Elnagar, Veerasathpurush Allareddy, Omar Suhaym, Rashid Ansari, Ahmet Enis Cetin
They also have a built-in set of novel directional filters that highlight the Cervical Verte edges in X-ray images.
no code implementations • 3 Oct 2022 • 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 parallel to achieve the same goal.
no code implementations • 7 Jan 2022 • Hongyi Pan, Diaa Badawi, Ishaan Bassi, Sule Ozev, Ahmet Enis Cetin
We propose a kernel-PCA based method to detect anomaly in chemical sensors.
no code implementations • 7 Jan 2022 • Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin
In both 1-D and 2-D layers, we compute the binary WHT of the input feature map and denoise the WHT domain coefficients using a nonlinearity which is obtained by combining soft-thresholding with the tanh function.
no code implementations • 22 Oct 2021 • Hongyi Pan, Diaa Badawi, Runxuan Miao, Erdem Koyuncu, Ahmet Enis Cetin
In this paper, we introduce multiplication-avoiding power iteration (MAPI), which replaces the standard $\ell_2$-inner products that appear at the regular power iteration (RPI) with multiplication-free vector products which are Mercer-type kernel operations related with the $\ell_1$ norm.
no code implementations • 25 May 2021 • Hongyi Pan, Diaa Badawi, Erdem Koyuncu, A. Enis Cetin
We consider a family of vector dot products that can be implemented using sign changes and addition operations only.
no code implementations • 14 Apr 2021 • 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 $1\times 1$ convolution layers in deep neural networks.