Comparer des méthodes

	Modèle de diffusion explicable	Modèle de diffusion auto-supervisé
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2020–2022	2020–2022
Auteur d'origine	Ho, J., Jain, A., & Abbeel, P. (DDPM, 2020); XAI augmentation by subsequent researchers	Ho, J. et al.; extended by Chen, T. et al. and subsequent self-supervised diffusion works
Type	Generative model with post-hoc or intrinsic explainability	Generative model with self-supervised representation objective
Source fondatrice	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851.	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.
Alias	XAI-DDPM, interpretable diffusion model, transparent diffusion model, explainable DDPM	SSDM, self-supervised score-based model, diffusion-based self-supervised learning, denoising diffusion with self-supervised pretraining
Apparentées	6	2
Résumé	An Explainable Diffusion Model couples a denoising diffusion probabilistic model with post-hoc or intrinsic explainability techniques — such as SHAP, gradient-based saliency, attention analysis, or concept-based probing — so that each generative or predictive decision can be audited and justified rather than treated as a black box.	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.