Comparer des méthodes

	Variational Autoencodeur à Adaptation de Domaine	Apprentissage par transfert
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2020	2010 (formalized); 1990s (early roots)
Auteur d'origine	Ilse, M.; Tomczak, J. M.; Louizos, C.; Welling, M.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Type	Generative model with domain adaptation	Learning paradigm
Source fondatrice	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.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Alias	DA-VAE, domain-adaptive VAE, domain-conditioned variational autoencoder, cross-domain VAE	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Apparentées	3	3
Résumé	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.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.