手法を比較

	自己教師あり変分オートエンコーダ	マルチモーダル変分オートエンコーダ
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2014 (VAE); self-supervised variant ~2019–2021	2018
提唱者	Kingma, D. P. & Welling, M. (VAE); self-supervised extensions by various authors from ~2019 onward	Wu, M. and Goodman, N.
種類	Generative model with self-supervised representation learning	Generative latent-variable model
原典	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014).	Wu, M., & Goodman, N. (2018). Multimodal Generative Models for Scalable Weakly-Supervised Learning. Advances in Neural Information Processing Systems (NeurIPS), 31.
別名	SS-VAE, self-supervised VAE, unsupervised VAE with self-supervised pretext tasks, contrastive VAE	MVAE, multimodal VAE, multi-modal variational autoencoder, multimodal generative model
関連	6	3
概要	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.	The Multimodal Variational Autoencoder (MVAE) is a deep generative model that learns a shared latent representation across two or more data modalities — such as images and captions — using a product-of-experts fusion of modality-specific encoders, enabling generation and inference even when only a subset of modalities is observed at test time.