Learning with not Enough Data Part 1: Semi-Supervised Learning

Linking pages

How to Train Really Large Models on Many GPUs? | Lil'Log https://lilianweng.github.io/posts/2021-09-25-train-large/ 33 comments
Learning with not Enough Data Part 3: Data Generation | Lil'Log https://lilianweng.github.io/posts/2022-04-15-data-gen/ 0 comments
Modern AI is Domestification https://thegradient.pub/ai-is-domestification/ 0 comments

Linked pages

How to Train Really Large Models on Many GPUs? | Lil'Log https://lilianweng.github.io/posts/2021-09-25-train-large/ 33 comments
Contrastive Representation Learning | Lil'Log https://lilianweng.github.io/posts/2021-05-31-contrastive/ 10 comments
[1905.11946] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks https://arxiv.org/abs/1905.11946 10 comments
[1904.12848] Unsupervised Data Augmentation for Consistency Training https://arxiv.org/abs/1904.12848 2 comments
[1703.01780] Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results https://arxiv.org/abs/1703.01780 1 comment
[1412.6572] Explaining and Harnessing Adversarial Examples http://arxiv.org/abs/1412.6572 1 comment
[2001.07685] FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence https://arxiv.org/abs/2001.07685 0 comments
[1911.04252] Self-training with Noisy Student improves ImageNet classification https://arxiv.org/abs/1911.04252 0 comments
[1909.13719] RandAugment: Practical automated data augmentation with a reduced search space https://arxiv.org/abs/1909.13719 0 comments
http://arxiv.org/abs/1603.09382 0 comments
[1905.02249] MixMatch: A Holistic Approach to Semi-Supervised Learning https://arxiv.org/abs/1905.02249 0 comments
[2006.10029] Big Self-Supervised Models are Strong Semi-Supervised Learners https://arxiv.org/abs/2006.10029 0 comments
[2006.06882] Rethinking Pre-training and Self-training https://arxiv.org/abs/2006.06882 0 comments
[1811.08883] Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883 0 comments