Comparer des méthodes

	Autoencodeur variationnel semi-supervisé	Apprentissage par transfert avec autoencodeur variationnel
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2014	2014 (VAE); 2010 (transfer learning survey)
Auteur d'origine	Kingma, D. P.; Mohamed, S.; Rezende, D. J.; Wierstra, D.	Kingma, D. P. & Welling, M. (VAE); transfer learning framework from Pan & Yang
Type	Generative probabilistic model (semi-supervised)	Generative model with transferred encoder/decoder
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.	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR 2014).
Alias	Semi-supervised VAE, M2 model, VAE with label propagation, deep generative semi-supervised model	TL-VAE, pretrained VAE, VAE transfer learning, fine-tuned variational autoencoder
Apparentées	6	6
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.	Transfer Learning with a Variational Autoencoder (TL-VAE) reuses an encoder and/or decoder pre-trained on a large source dataset and adapts it to a smaller target domain. By inheriting a rich probabilistic latent space rather than starting from random weights, TL-VAE dramatically reduces the amount of target-domain data needed for high-quality generation or representation learning.