Papers of the day   All papers

AutoAugment: Learning Augmentation Strategies from Data


Google AI: Introducing SimCLR, a new approach to self- and semi-supervised learning that can learn good image representations without requiring human annotations, and achieves a new state of the art on ImageNet when fine-tuned on only 1% labeled data. Learn more at

12 replies, 1020 likes

Xander Steenbrugge: Self-supervised learning is starting to work **very** well thanks to contrastive losses: @ylecun's cake🥮 is growing! Next step: combine this with fully learnable augmentations (~ + insight into how these influence the final representations wrt new tasks

2 replies, 153 likes

hardmaru: Papers excluding first (NAS) and last point: • better activation functions • better learning rules • better data augmentation • better loss functions &

3 replies, 152 likes

William Hsu: Interesting use of reinforcement learning to optimize data augmentation. Instead of performing a fixed number of transformations, a search is used to identify a set of operations and their ordering that yields the best validation accuracy. #CVPR2019

0 replies, 1 likes


Found on Apr 08 2020 at

PDF content of a computer science paper: AutoAugment: Learning Augmentation Strategies from Data