Comparer des méthodes

	Autoencodeur variationnel semi-supervisé	CNN convolutive semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2014	2013–2017
Auteur d'origine	Kingma, D. P.; Mohamed, S.; Rezende, D. J.; Wierstra, D.	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
Type	Generative probabilistic model (semi-supervised)	Semi-supervised deep learning
Source fondatrice	Kingma, D. P., Mohamed, S., Rezende, D. J., & Wierstra, D. (2014). Semi-supervised learning with deep generative models. Advances in Neural Information Processing Systems (NeurIPS), 27, 3581–3589.	Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning.
Alias	Semi-supervised VAE, M2 model, VAE with label propagation, deep generative semi-supervised model	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
Apparentées	6	5
Résumé	The semi-supervised VAE (M2 model) is a deep generative method that jointly learns a latent representation of inputs and a classifier, leveraging both labeled and unlabeled examples in a principled probabilistic framework. Introduced by Kingma et al. in 2014, it allows accurate classification even when labels are scarce by having the generative model explain away unlabeled observations.	A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort.