Wasserstein Generative Adversarial Network

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 extending WGANs for conditional generation, addressing data scarcity through augmentation, and improving their application in diverse fields like image generation, time series analysis, and inverse problems. This work is significant because WGANs offer a robust framework for generating high-quality synthetic data, enabling advancements in areas with limited real-world data and facilitating improved model training and performance in various applications.

Papers

July 25, 2022

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Massimiliano Lupo Pasini, Junqi Yin
Conditional Generative Adversarial Network GAN Training ImageNet 1k GAN Based Wasserstein Generative Adversarial Network

June 15, 2022

Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?
Alexander Korotin, Alexander Kolesov, Evgeny Burnaev
Optimal Transport Variational Method Wasserstein Generative Adversarial Network Wasserstein Gan Kantorovich Potential

June 6, 2022

Scene Aware Person Image Generation through Global Contextual Conditioning
Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein
Image Generation Generative Network Wasserstein Generative Adversarial Network Web Screenshots Person Image Generation

June 3, 2022

Causality Learning With Wasserstein Generative Adversarial Networks
Hristo Petkov, Colin Hanley, Feng Dong
Causal Structure Directed Acyclic Graph Causal Structure Learning Wasserstein Generative Adversarial Network Causality Based Learning

May 23, 2022

Wasserstein Generative Adversarial Networks for Online Test Generation for Cyber Physical Systems
Jarkko Peltomäki, Frankie Spencer, Ivan Porres
Level Test Cyber Physical Test Generation Wasserstein Generative Adversarial Network Test Data Generation

April 1, 2022

DAG-WGAN: Causal Structure Learning With Wasserstein Generative Adversarial Networks
Hristo Petkov, Colin Hanley, Feng Dong
Generative Model Causal Structure Causal Structure Learning Wasserstein Generative Adversarial Network

March 22, 2022

Conditional Generative Data Augmentation for Clinical Audio Datasets
Matthias Seibold, Armando Hoch, Mazda Farshad, Nassir Navab, Philipp Fürnstahl
Wasserstein Generative Adversarial Network Audio Augmentation

March 12, 2022

Wasserstein Adversarial Transformer for Cloud Workload Prediction
Shivani Arbat, Vinodh Kumaran Jayakumar, Jaewoo Lee, Wei Wang, In Kee Kim
Wasserstein Generative Adversarial Network Predictive Learning Cloud Workload

March 4, 2022

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration
Zi-Ming Wang, Nan Xue, Ling Lei, Gui-Song Xia
Distribution Matching Wasserstein Gradient Non Rigid Registration Wasserstein Generative Adversarial Network Point Set

December 7, 2021

Generative Adversarial Networks for Data Generation in Structural Health Monitoring
Furkan Luleci, F. Necati Catbas, Onur Avci
Generative Adversarial Network Data Generation Structural Health Monitoring Damage Detection Wasserstein Generative Adversarial Network