手法を比較

	説明可能なGAN	Variational Autoencoder
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2019 (GAN Dissection); ongoing	2014
提唱者	Bau, D. et al. (GAN Dissection); broader XAI-GAN community	Kingma, D. P. & Welling, M.
種類	Explainable generative model	Deep generative latent-variable model (encoder–decoder)
原典	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).	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
別名	XAI-GAN, Interpretable GAN, Transparent GAN, Explainable Generative Model	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
関連	4	5
概要	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.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.