Meta Pseudo Labels — mentioned by Veedrac

Sun, 04 Apr 2021 12:50:04 GMT

This article doesn't make any major factual errors, but it's implicating that this is some sort of surprise, and that it's a major impediment, neither or which hold up. While training on noisy datasets is an interesting problem for many practical use-cases, a few percent label errors in these classic basic datasets (MNIST, CIFAR, ImageNet) really doesn't matter that much. The first two are basically toys to check that your system works at all at this point, and even on ImageNet the best models are now more accurate than the original labels. However, per [1], progress on current ImageNet still…

Paper and discussion history. A mention is not an endorsement.

Meta Pseudo Labels · HackerPapers discussions

Meta Pseudo Labels — mentioned by Veedrac