Facebook’s new computer vision model achieves state-of-the-art performance by learning from random images

Join Transform 2021 for the most important themes in enterprise AI & Data. Learn more. Facebook today announced that it’s created an AI model trained on a billion images that ostensibly achieves state-of-the-art results in a range of computer vision benchmarks. Unlike most computer vision models, which learn from labeled data sets, Facebo…Read More

via VentureBeat

Check out the Finding Your Identity Podcast!