Generative Adversarial Network
Generative Adversarial Networks (GANs) are a class of deep learning models designed to generate new data instances that resemble a training dataset. Current research focuses on improving GAN training stability, enhancing the quality and diversity of generated data, and applying GANs to diverse fields like medical imaging, drug discovery, and time series analysis, often incorporating techniques like contrastive learning and disentangled representation learning to improve model performance and interpretability. The ability of GANs to synthesize realistic data addresses critical limitations in data availability and annotation costs across numerous scientific disciplines and practical applications, leading to advancements in areas ranging from medical diagnosis to robotic control.
Papers
A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN)
Jennifer Sleeman, David Chung, Anand Gnanadesikan, Jay Brett, Yannis Kevrekidis, Marisa Hughes, Thomas Haine, Marie-Aude Pradal, Renske Gelderloos, Chace Ashcraft, Caroline Tang, Anshu Saksena, Larry White
Generative Adversarial Networks for Malware Detection: a Survey
Aeryn Dunmore, Julian Jang-Jaccard, Fariza Sabrina, Jin Kwak
TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation
Yunliang Jiang, Lili Yan, Xiongtao Zhang, Yong Liu, Danfeng Sun
Optimal Transport Guided Unsupervised Learning for Enhancing low-quality Retinal Images
Wenhui Zhu, Peijie Qiu, Mohammad Farazi, Keshav Nandakumar, Oana M. Dumitrascu, Yalin Wang
Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
Lyle Regenwetter, Akash Srivastava, Dan Gutfreund, Faez Ahmed
GAN-based Vertical Federated Learning for Label Protection in Binary Classification
Yujin Han, Leying Guan
This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation
Dimitrios E. Diamantis, Panagiota Gatoula, Anastasios Koulaouzidis, Dimitris K. Iakovidis
MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoders
Naser Damer, Meiling Fang, Patrick Siebke, Jan Niklas Kolf, Marco Huber, Fadi Boutros
Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks
Bowen Tian, Qinliang Su, Jianxing Yu
Learning End-to-End Channel Coding with Diffusion Models
Muah Kim, Rick Fritschek, Rafael F. Schaefer
GTV: Generating Tabular Data via Vertical Federated Learning
Zilong Zhao, Han Wu, Aad Van Moorsel, Lydia Y. Chen