CoAtNet: Marrying Convolution and Attention for All Data Sizes Updated: August 24, 2021 5 minute read
Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length Updated: July 8, 2021 5 minute read
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet Updated: July 2, 2021 4 minute read
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Updated: June 29, 2021 5 minute read
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning(2020) Updated: July 29, 2020 4 minute read
CoAtNet: Marrying Convolution and Attention for All Data Sizes Updated: August 24, 2021 5 minute read
Sharpness-Aware Minimization for efficiently improving generalization Updated: August 10, 2021 6 minute read
When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations Updated: July 30, 2021 5 minute read
Unsupervised Data Augmentation for Consistency Training(2019) Updated: January 14, 2021 3 minute read
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning(2017) Updated: January 13, 2021 3 minute read
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results(2017) Updated: January 11, 2021 1 minute read
Self-training with Noisy Student improves ImageNet classification(2019) Updated: July 8, 2020 4 minute read
RandAugment: Practical automated data augmentation with a reduced search space Updated: June 24, 2021 5 minute read