Comparer des méthodes

	Autoencodeur variationnel faiblement supervisé	Réseau antagoniste génératif
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2014–2018	2014
Auteur d'origine	Kingma, D. P. et al. (building on VAE and semi-supervised deep generative models)	Goodfellow, I. et al.
Type	Generative model with weak supervision	Generative deep learning (adversarial two-network game)
Source fondatrice	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the International Conference on Learning Representations (ICLR 2014).	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
Alias	WS-VAE, weakly-supervised VAE, semi-supervised VAE with weak labels, label-guided variational autoencoder	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Apparentées	3	4
Résumé	A Weakly Supervised Variational Autoencoder (WS-VAE) extends the standard VAE generative framework by incorporating partial, noisy, or coarse supervision signals — such as crowd-sourced labels, heuristic rules, or programmatic annotations — to guide latent space learning without requiring fully annotated data. It is widely applied in computer vision, NLP, and biomedical domains where complete ground-truth labels are expensive or unavailable.	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.