Comparer des méthodes

	GAN faiblement supervisé	Modèle de diffusion
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2014–2017	2020
Auteur d'origine	Odena et al.; building on Goodfellow et al. (2014)	Ho, J., Jain, A. & Abbeel, P.
Type	Generative model with weak supervision	Generative deep learning (denoising diffusion)
Source fondatrice	Odena, A., Olah, C., & Shlens, J. (2017). Conditional Image Synthesis with Auxiliary Classifier GANs. Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR 70, 2642–2651.	Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS.
Alias	WS-GAN, weakly supervised generative adversarial network, label-efficient GAN, semi-labeled GAN	Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM
Apparentées	5	4
Résumé	A Weakly Supervised GAN is a generative adversarial network trained with partially labeled, noisily labeled, or coarse-annotation data instead of fully annotated ground truth. It extends the standard GAN framework so that limited supervision guides conditional generation or discriminative learning, enabling high-quality data synthesis and classification in label-scarce settings.	A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling.