手法を比較

	説明可能な拡散モデル	説明可能なGAN
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2020–2022	2019 (GAN Dissection); ongoing
提唱者	Ho, J., Jain, A., & Abbeel, P. (DDPM, 2020); XAI augmentation by subsequent researchers	Bau, D. et al. (GAN Dissection); broader XAI-GAN community
種類	Generative model with post-hoc or intrinsic explainability	Explainable generative model
原典	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851.	Bau, D., Zhu, J.-Y., Strobelt, H., Zhou, B., Tenenbaum, J. B., Freeman, W. T., & Torralba, A. (2019). GAN Dissection: Visualizing and Understanding Generative Adversarial Networks. In Proceedings of the International Conference on Learning Representations (ICLR 2019).
別名	XAI-DDPM, interpretable diffusion model, transparent diffusion model, explainable DDPM	XAI-GAN, Interpretable GAN, Transparent GAN, Explainable Generative Model
関連	6	4
概要	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.	Explainable GAN applies interpretability techniques to Generative Adversarial Networks to reveal which internal units and latent directions cause specific visual or structural features in generated outputs. It combines GAN training with post-hoc analysis tools — such as unit dissection, saliency maps, or disentangled latent spaces — to make generative model behaviour transparent and auditable.