Semi-supervised learning is an approach to machine learning that combines a small amount of labeled data with a large amount of unlabeled data during training. Semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data).
It is a special instance of weak supervision. [Wiki]
0) Introduction:
Purpose:
Metrics:
Dataset:
The authors simulate a low-data regime by using only a small portion (e.g. 40/250/4000/10000 examples) of the whole dataset as labeled and treating the remaining as the unlabeled set.
1) Methods:
1. Self-training:
Pseudo-label
Noisy Student
2. Consistency Regularization:
π-model
Temporal Ensembling
Mean Teacher
Virtual Adversarial Training (VAT)
Unsupervised Data Augmentation (UDA)
3. Hybrid Methods:
UnMix
MixMatch
ReMixMatch
FixMatch
References:
