AutoAugment: Learning Augmentation Policies from Data · HackerPapers discussions

AutoAugment: Learning Augmentation Policies from Data — mentioned by p1esk

Fri, 03 May 2019 17:15:34 GMT

FYI, they compare their cifar results to [1], which is more effective than plain cutout. [1] https://arxiv.org/abs/1805.09501

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

Tue, 14 Aug 2018 16:33:23 GMT

This is two years out of date. Current state of the art for CIFAR has about 1/4th of the errors https://arxiv.org/abs/1805.09501

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

Wed, 20 Jun 2018 12:05:28 GMT

Direct link to the paper: https://arxiv.org/abs/1805.09501 PDF: https://arxiv.org/pdf/1805.09501.pdf

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