Methoden vergleichen

	Transfer Learning mit Variational Autoencoder	Semi-supervised Variational Autoencoder
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	2014 (VAE); 2010 (transfer learning survey)	2014
Urheber	Kingma, D. P. & Welling, M. (VAE); transfer learning framework from Pan & Yang	Kingma, D. P.; Mohamed, S.; Rezende, D. J.; Wierstra, D.
Typ	Generative model with transferred encoder/decoder	Generative probabilistic model (semi-supervised)
Wegweisende Quelle	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR 2014).	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.
Aliasnamen	TL-VAE, pretrained VAE, VAE transfer learning, fine-tuned variational autoencoder	Semi-supervised VAE, M2 model, VAE with label propagation, deep generative semi-supervised model
Verwandt	6	6
Zusammenfassung	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.	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.