Wasserstein Gan

Wasserstein Generative Adversarial Networks (WGANs) are generative models that leverage the Wasserstein distance to improve training stability and sample quality compared to traditional GANs. Current research focuses on refining WGAN architectures, such as incorporating gradient penalties or integrating them with other models like Pix2Pix or autoencoders, to address challenges like mode collapse and improve performance in diverse applications. These advancements are significantly impacting fields ranging from image denoising and super-resolution to data augmentation for tasks with limited datasets, demonstrating the broad utility of WGANs in various scientific and practical domains.

Papers

November 10, 2024

A Hybrid Approach for COVID-19 Detection: Combining Wasserstein GAN with Transfer Learning
Sumera Rounaq, Shahid Munir Shah, Mahmoud Aljawarneh, Sarah Khan, Ghulam Muhammad
Transfer Learning Covid 19 COVID 19 Detection Hybrid Approach COVID 19 Case Wasserstein Gan Ventilator Associated Pneumonia Early Diagnosis

November 6, 2024

Calibrating for the Future:Enhancing Calorimeter Longevity with Deep Learning
S. Ali, A.S. Ryzhikov, D.A. Derkach, F.D. Ratnikov, V.O. Bocharnikov
LeArning Abstract Future Reasoning High Energy Physic Wasserstein Gan Calorimeter Simulation Particle Physic

September 27, 2024

Adaptive Learning of the Latent Space of Wasserstein Generative Adversarial Networks
Yixuan Qiu, Qingyi Gao, Xiao Wang
Generative Model Generative Adversarial Network Latent Space Adaptive Learning Wasserstein Generative Adversarial Network Wasserstein Gan Latent Dimension

July 16, 2024

Novel Hybrid Integrated Pix2Pix and WGAN Model with Gradient Penalty for Binary Images Denoising
Luca Tirel, Ali Mohamed Ali, Hashim A. Hashim
Generative Adversarial Network Image Denoising GAN Training Wasserstein Gan Gradient Penalty

May 25, 2024

A Differential Equation Approach for Wasserstein GANs and Beyond
Zachariah Malik, Yu-Jui Huang
Generative Adversarial Network Adversarial Training Differential Equation Continual Training Wasserstein Gan GAN Algorithm

May 22, 2024

Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
Sixin Zhang
Riemannian Geometry Local Convergence Wasserstein Gan Equilibrium State Stackelberg Equilibrium Differentiable Game

March 22, 2024

A Wasserstein perspective of Vanilla GANs
Lea Kunkel, Mathias Trabs
Generative Adversarial Network Wasserstein Distance Wasserstein Gan

February 5, 2024

Improving EEG Signal Classification Accuracy Using Wasserstein Generative Adversarial Networks
Joshua Park, Priyanshu Mahey, Ore Adeniyi
EEG Signal EEG Classification Wasserstein Generative Adversarial Network Wasserstein Gan

October 25, 2023

An Explainable Deep Learning-Based Method For Schizophrenia Diagnosis Using Generative Data-Augmentation
Mehrshad Saadatinia, Armin Salimi-Badr
Variational Autoencoder Automatic Diagnosis Generative Data Augmentation Schizophrenia Diagnosis Wasserstein Gan Learning Based Method

October 12, 2023

Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN
Una M. Kelly, Meike Nauta, Lu Liu, Luuk J. Spreeuwers, Raymond N. J. Veldhuis
Generative Adversarial Network Wasserstein Generative Adversarial Network Wasserstein Gan Worst Case Morphs

July 31, 2023

Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
Elen Vardanyan, Sona Hunanyan, Tigran Galstyan, Arshak Minasyan, Arnak Dalalyan
Generative Model Latent Space Generative Modeling Probabilistic Generative Model Wasserstein Gan Least Absolute Deviation Empirical Distribution

July 19, 2023

Adversarial Likelihood Estimation With One-Way Flows
Omri Ben-Dov, Pravir Singh Gupta, Victoria Abrevaya, Michael J. Black, Partha Ghosh
Generative Adversarial Network GAN Model Adversarial Framework Wasserstein Gan Adversarial Estimator Bidirectional Flow

July 14, 2023

Generative adversarial networks for data-scarce spectral applications
Juan José García-Esteban, Juan Carlos Cuevas, Jorge Bravo-Abad
Generative Adversarial Network Adversarial Learning Generative Question Wasserstein Generative Adversarial Network Wasserstein Gan Synthetic Spectrum Spectral Band

March 24, 2023

A Three-Player GAN for Super-Resolution in Magnetic Resonance Imaging
Qi Wang, Lucas Mahler, Julius Steiglechner, Florian Birk, Klaus Scheffler, Gabriele Lohmann
Generative Adversarial Network Super Resolution Magnetic Resonance Imaging GAN Training Magnetic Resonance Wasserstein Gan GAN Loss

February 27, 2023

Stock Broad-Index Trend Patterns Learning via Domain Knowledge Informed Generative Network
Jingyi Gu, Fadi P. Deek, Guiling Wang
Generative Adversarial Network GAN Model Wasserstein Gan Stock Movement Prediction

February 17, 2023

PAC-Bayesian Generalization Bounds for Adversarial Generative Models
Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain
Generative Model Generalization Bound Wasserstein Gan PAC Bayesian Generalization Bound Non Vacuous Generalization Bound

February 3, 2023

Learning End-to-End Channel Coding with Diffusion Models
Muah Kim, Rick Fritschek, Rafael F. Schaefer
Diffusion Model Generative Model Generative Adversarial Network Differentiable Channel Wasserstein Gan

November 23, 2022

Completing point cloud from few points by Wasserstein GAN and Transformers
Xianfeng Wu, Jinhui Qian, Qing Wei, Xianzu Wu, Xinyi Liu, Luxin Hu, Yanli Gong, Zhongyuan Lai, Libing Wu
Point Cloud Transformer Megatron Decepticons GAN Model Encoder Decoder Exceptional Point Wasserstein Gan Partial Point Cloud High Level Vision Task

October 28, 2022

Towards prediction of turbulent flows at high Reynolds numbers using high performance computing data and deep learning
Mathis Bode, Michael Gauding, Jens Henrik Göbbert, Baohao Liao, Jenia Jitsev, Heinz Pitsch
Deep Learning Generative Adversarial Network Human Prediction High Performance Computing Turbulent Flow Wasserstein Gan Turbulence Model Reynolds Number

October 25, 2022

'A net for everyone': fully personalized and unsupervised neural networks trained with longitudinal data from a single patient
Christian Strack, Kelsey L. Pomykala, Heinz-Peter Schlemmer, Jan Egger, Jens Kleesiek
Neural Network Deep Neural Network Generative Adversarial Network Single Modality Longitudinal Data Wasserstein Gan Personalized Medicine

Wasserstein Gan

Papers

A Hybrid Approach for COVID-19 Detection: Combining Wasserstein GAN with Transfer Learning

Calibrating for the Future:Enhancing Calorimeter Longevity with Deep Learning

Adaptive Learning of the Latent Space of Wasserstein Generative Adversarial Networks

Novel Hybrid Integrated Pix2Pix and WGAN Model with Gradient Penalty for Binary Images Denoising

A Differential Equation Approach for Wasserstein GANs and Beyond

Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold

A Wasserstein perspective of Vanilla GANs

Improving EEG Signal Classification Accuracy Using Wasserstein Generative Adversarial Networks

An Explainable Deep Learning-Based Method For Schizophrenia Diagnosis Using Generative Data-Augmentation

Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN

Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution

Adversarial Likelihood Estimation With One-Way Flows

Generative adversarial networks for data-scarce spectral applications

A Three-Player GAN for Super-Resolution in Magnetic Resonance Imaging

Stock Broad-Index Trend Patterns Learning via Domain Knowledge Informed Generative Network

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

Learning End-to-End Channel Coding with Diffusion Models

Completing point cloud from few points by Wasserstein GAN and Transformers

Towards prediction of turbulent flows at high Reynolds numbers using high performance computing data and deep learning

'A net for everyone': fully personalized and unsupervised neural networks trained with longitudinal data from a single patient