GANetic Loss

GANetic loss is a novel loss function designed to improve the training stability and performance of Generative Adversarial Networks (GANs), a class of machine learning models used for tasks like image generation and anomaly detection. Research focuses on optimizing GAN loss functions, exploring both the development of new functions like GANetic loss and the unification of existing ones through parameterized frameworks. This work aims to address the inherent instability of GAN training, leading to more reliable and reproducible results across diverse applications, including medical imaging.

Papers

June 7, 2024

GANetic Loss for Generative Adversarial Networks with a Focus on Medical Applications
Shakhnaz Akhmedova, Nils Körber
Generative Adversarial Network Loss Function Human Driving Focus GAN Training Medical Application GANetic Loss

August 14, 2023

A Unifying Generator Loss Function for Generative Adversarial Networks
Justin Veiner, Fady Alajaji, Bahman Gharesifard
Generative Adversarial Network GANetic Loss

February 14, 2023

On Classification-Calibration of Gamma-Phi Losses
Yutong Wang, Clayton D. Scott
Class Loss Classifier Calibration Classification Loss Function GANetic Loss

GANetic Loss

Papers

GANetic Loss for Generative Adversarial Networks with a Focus on Medical Applications

A Unifying Generator Loss Function for Generative Adversarial Networks

On Classification-Calibration of Gamma-Phi Losses