手法を比較

	自己教師あり拡散モデル	Generative Adversarial Network
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2020–2022	2014
提唱者	Ho, J. et al.; extended by Chen, T. et al. and subsequent self-supervised diffusion works	Goodfellow, I. et al.
種類	Generative model with self-supervised representation objective	Generative deep learning (adversarial two-network game)
原典	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
別名	SSDM, self-supervised score-based model, diffusion-based self-supervised learning, denoising diffusion with self-supervised pretraining	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
関連	2	4
概要	A self-supervised diffusion model couples the iterative noise-and-denoise generative process of denoising diffusion probabilistic models with a self-supervised representation learning objective — such as contrastive or masked prediction loss — so that the model simultaneously learns to generate realistic data and to produce semantically meaningful representations without any labeled examples.	A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.