3 citations · 7 across the 24 of their papers we have counts for
26 papers
Learned Queries and Keys Are All You Need: Replacing the Value Projection with Structured Transforms
Ene Meco, Emadeldeen Hamdan, A. Enis Cetin
To reduce the number of parameters and cache memory requirements of transformers we introduce dual-headed transformers instead of three heads. We studied Walsh-Hadamard Transform (…
Image Reconstruction from Phase with Untrained Neural Priors
Ene Meco, Ahmet Enis Cetin
Fourier phase encodes important spatial image structure, but recovering an image without measured spectral magnitude requires additional constraints and leaves absolute intensity a…
WHTMix: Efficient Stereo Depth Estimation via Walsh-Hadamard Token Mixing
Prathyush Sajith, Emadeldeen Hamdan, Ahmet Enis Cetin
Stereo depth estimation for driving, robotics and augmented reality must run at high resolution under tight latency budgets, yet in transformer-based matchers the global self-atten…
ShearFuse-UNet: Hadamard, DCT, and Shearlet Transform Fusion for Next-Day Wildfire Spread Prediction
Ene Meco, Yingyi Luo, Emadeldeen Hamdan +2
We propose ShearFuse-UNet, a lightweight and computationally efficient deep learning model for next-day wildfire spread prediction from multi-modal satellite data. The model integr…
DynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imagings
Vittorio Palladino, Ahmet Enis Cetin
Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measurements. While deep le…
WTHaar-Net: a Hybrid Quantum-Classical Approach
Vittorio Palladino, Tsai Idden, Ahmet Enis Cetin
Convolutional neural networks rely on linear filtering operations that can be reformulated efficiently in suitable transform domains. At the same time, advances in quantum computin…
Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptation
Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir +4
Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video datasets. However, peatland fires exhibit…
U-Net with Hadamard Transform and DCT Latent Spaces for Next-day Wildfire Spread Prediction
Yingyi Luo, Shuaiang Rong, Adam Watts +1
We developed a lightweight and computationally efficient tool for next-day wildfire spread prediction using multimodal satellite data as input. The deep learning model, which we ca…
HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing
Emadeldeen Hamdan, Ahmet Enis Cetin
Reducing the cost of multiplications is critical for efficient deep neural network deployment, especially in energy-constrained edge devices. In this work, we introduce HTMA-Net, a…
VHU-Net: Variational Hadamard U-Net for Body MRI Bias Field Correction
Xin Zhu, Ahmet Enis Cetin, Gorkem Durak +13
Bias field artifacts in magnetic resonance imaging (MRI) scans introduce spatially smooth intensity inhomogeneities that degrade image quality and hinder downstream analysis. To ad…
Shifts in Doctors' Eye Movements Between Real and AI-Generated Medical Images
David C Wong, Bin Wang, Gorkem Durak +21
Eye-tracking analysis plays a vital role in medical imaging, providing key insights into how radiologists visually interpret and diagnose clinical cases. In this work, we first ana…
Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging
David Wong, Bin Wang, Gorkem Durak +23
The demand for high-quality synthetic data for model training and augmentation has never been greater in medical imaging. However, current evaluations predominantly rely on computa…
Edge-Fog Computing-Enabled EEG Data Compression via Asymmetrical Variational Discrete Cosine Transform Network
Xin Zhu, Hongyi Pan, Ahmet Enis Cetin
The large volume of electroencephalograph (EEG) data produced by brain-computer interface (BCI) systems presents challenges for rapid transmission over bandwidth-limited channels i…
Efficient Bearing Sensor Data Compression via an Asymmetrical Autoencoder with a Lifting Wavelet Transform Layer
Xin Zhu, Ahmet Enis Cetin
Bearing data compression is vital to manage the large volumes of data generated during condition monitoring. In this paper, a novel asymmetrical autoencoder with a lifting wavelet…
Sparse Mamba: Introducing Controllability, Observability, And Stability To Structural State Space Models
Emadeldeen Hamdan, Hongyi Pan, Ahmet Enis Cetin
Structured state space models' (SSMs) development in recent studies, such as Mamba and Mamba2, outperformed and solved the computational inefficiency of transformers and large lang…
Ethical Framework for Responsible Foundational Models in Medical Imaging
Debesh Jha, Gorkem Durak, Abhijit Das +33
The emergence of foundational models represents a paradigm shift in medical imaging, offering extraordinary capabilities in disease detection, diagnosis, and treatment planning. Th…
Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers
Hongyi Pan, Emadeldeen Hamdan, Xin Zhu +2
Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and co…
The Blind Normalized Stein Variational Gradient Descent-Based Detection for Intelligent Random Access in Cellular IoT
Xin Zhu, Ahmet Enis Cetin
The lack of an efficient preamble detection algorithm remains a challenge for solving preamble collision problems in intelligent random access (RA) in the cellular Internet of Thin…
A Probabilistic Hadamard U-Net for MRI Bias Field Correction
Xin Zhu, Hongyi Pan, Yury Velichko +5
Magnetic field inhomogeneity correction remains a challenging task in MRI analysis. Most established techniques are designed for brain MRI by supposing that image intensities in th…
A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression
Xin Zhu, Daoguang Yang, Hongyi Pan +3
The lack of an efficient compression model remains a challenge for the wireless transmission of gearbox data in non-contact gear fault diagnosis problems. In this paper, we present…
Electroencephalogram Sensor Data Compression Using An Asymmetrical Sparse Autoencoder With A Discrete Cosine Transform Layer
Xin Zhu, Hongyi Pan, Shuaiang Rong +1
Electroencephalogram (EEG) data compression is necessary for wireless recording applications to reduce the amount of data that needs to be transmitted. In this paper, an asymmetric…
ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation
Nastaran Darabi, Maeesha Binte Hashem, Hongyi Pan +3
The edge processing of deep neural networks (DNNs) is becoming increasingly important due to its ability to extract valuable information directly at the data source to minimize lat…
Domain Generalization with Fourier Transform and Soft Thresholding
Hongyi Pan, Bin Wang, Zheyuan Zhang +5
Domain generalization aims to train models on multiple source domains so that they can generalize well to unseen target domains. Among many domain generalization methods, Fourier-t…
Stein Variational Gradient Descent-based Detection For Random Access With Preambles In MTC
Xin Zhu, Hongyi Pan, Salih Atici +1
Traditional preamble detection algorithms have low accuracy in the grant-based random access scheme in massive machine-type communication (mMTC). We present a novel preamble detect…