Porovnat metody

	Doménově adaptovaný varianční autoenkodér	Variační autoenkodér
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2020	2014
Tvůrce	Ilse, M.; Tomczak, J. M.; Louizos, C.; Welling, M.	Kingma, D. P. & Welling, M.
Typ	Generative model with domain adaptation	Deep generative latent-variable model (encoder–decoder)
Původní zdroj	Ilse, M., Tomczak, J. M., Louizos, C., & Welling, M. (2020). DIVA: Domain Invariant Variational Autoencoders. Proceedings of the Third Conference on Medical Imaging with Deep Learning (MIDL 2020), PMLR 121, 322–348.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Další názvy	DA-VAE, domain-adaptive VAE, domain-conditioned variational autoencoder, cross-domain VAE	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Příbuzné	3	5
Shrnutí	A Domain-Adaptive Variational Autoencoder (DA-VAE) extends the standard VAE framework to learn disentangled latent representations that separate domain-specific variation from class-relevant and domain-invariant content, enabling models trained on a source domain to generalise effectively to a different but related target domain with limited or no target labels.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.