3 papers
cs.LG2023
Addressing GAN Training Instabilities via Tunable Classification Losses
Monica Welfert, Gowtham R. Kurri, Kyle Otstot +1
Generative adversarial networks (GANs), modeled as a zero-sum game between a generator (G) and a discriminator (D), allow generating synthetic data with formal guarantees. Noting t…
cs.LG2023
-GANs: Addressing GAN Training Instabilities via Dual Objectives
Monica Welfert, Kyle Otstot, Gowtham R. Kurri +1
In an effort to address the training instabilities of GANs, we introduce a class of dual-objective GANs with different value functions (objectives) for the generator (G) and discri…
cs.LG2022
AugLoss: A Robust Augmentation-based Fine Tuning Methodology
Kyle Otstot, Andrew Yang, John Kevin Cava +1
Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training sta…