手法を比較

	自己教師ありGAN (Self-supervised GAN)	自己教師あり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	2019	2014 (VAE); self-supervised variant ~2019–2021
提唱者	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N.	Kingma, D. P. & Welling, M. (VAE); self-supervised extensions by various authors from ~2019 onward
種類	Generative model with self-supervised auxiliary tasks	Generative model with self-supervised representation learning
原典	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. (2019). Self-Supervised GANs via Auxiliary Rotation Loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12154–12163.	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014).
別名	SS-GAN, Self-supervised GAN, Self-supervised Generative Adversarial Network, GAN with self-supervised auxiliary tasks	SS-VAE, self-supervised VAE, unsupervised VAE with self-supervised pretext tasks, contrastive VAE
関連	5	6
概要	Self-supervised GAN augments a standard Generative Adversarial Network with one or more self-supervised auxiliary tasks — such as predicting image rotation or patch position — that stabilise adversarial training and yield a discriminator that learns rich, transferable representations from unlabeled data without requiring manual annotations.	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.