Please enable JavaScript.
Coggle requires JavaScript to display documents.
Semi-supervised
Learning - Coggle Diagram
Semi-supervised
Learning
History
Γ Model: Semi-supervised learning with ladder networks, 2015
Π Model & Temporal ensembling Model: Temporal ensembling for semi-supervised learning, 2017
Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks, 2013
VAT：Virtual Adversarial Training: a Regularization Method for Supervised and Semi-supervised Learning, 2017
Mean Teacher：Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results，2018
MixMatch: A Holistic Approach to Semi-Supervised Learning, 2019
Unsupervised Data Augmentation (UDA) for Consistency Training, 2019
-
Purpose
It is hoped that through a small amount of labeled data annotated by experts, combined with a large amount of unlabeled data, a model with strong generalization ability will be trained ;
-
-