NVIDIA Research Achieves AI Training Breakthrough Using Limited Datasets
AI News Sharing
NVIDIA researchers achieved a data augmentation breakthrough with their newest GAN, requiring 10-20x less training images. Their AI model emulates artwork from a small dataset from the Metropolitan Museum of Art — and opening up new potential applications in fields like healthcare.
This new method is the latest in a legacy of GAN innovation by NVIDIA researchers, who’ve developed groundbreaking GAN-based models for the AI painting app GauGAN, the game engine mimicker GameGAN, and the pet photo transformer GANimal. All are available on the NVIDIA AI Playground.
Read Full Article Here