ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3222044
Abstract: Data augmentation (DA) is a widely used technique for enhancing the training of deep neural networks. Recent DA techniques which achieve state-of-the-art performance always meet the need for diversity in augmented training samples. However, an… read more here.
Keywords: ood; resmooth detecting; data augmentation; ood samples ... See more keywords
ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.48550/arxiv.2210.15137
Abstract: Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness, it is difficult for these methods… read more here.
Keywords: scoremix scalable; training; scalable augmentation; augmentation ... See more keywords