방법 비교

	준지도 학습 변이형 오토인코더	자기 지도 변분형 오토인코더
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2014	2014 (VAE); self-supervised variant ~2019–2021
창시자	Kingma, D. P.; Mohamed, S.; Rezende, D. J.; Wierstra, D.	Kingma, D. P. & Welling, M. (VAE); self-supervised extensions by various authors from ~2019 onward
유형	Generative probabilistic model (semi-supervised)	Generative model with self-supervised representation learning
원전	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. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014).
별칭	Semi-supervised VAE, M2 model, VAE with label propagation, deep generative semi-supervised model	SS-VAE, self-supervised VAE, unsupervised VAE with self-supervised pretext tasks, contrastive VAE
관련	6	6
요약	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 Self-supervised Variational Autoencoder (SS-VAE) combines the generative latent-space learning of a standard VAE with self-supervised pretext tasks — such as contrastive augmentation, masked reconstruction, or rotation prediction — to learn richer, more disentangled representations from unlabeled data without any manual annotation.