Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| Generative Adversarial Network× | Wasserstein GAN (WGAN)× | |
|---|---|---|
| Camp | Aprenentatge profund | Aprenentatge profund |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 2014 | 2017 |
| Autor original≠ | Goodfellow, I. et al. | Martín Arjovsky, Soumith Chintala & Léon Bottou |
| Tipus≠ | Generative deep learning (adversarial two-network game) | Generative adversarial network variant |
| Font seminal≠ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ | Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223. link ↗ |
| Àlies | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network | WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN |
| Relacionats≠ | 4 | 3 |
| Resum≠ | 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. | Wasserstein GAN (WGAN) is a generative adversarial network variant introduced by Arjovsky, Chintala, and Bottou in 2017 that replaces the Jensen-Shannon divergence used in the original GAN with the Wasserstein-1 (Earth Mover) distance. This substitution provides a theoretically grounded training objective that yields more stable optimization and a loss value that correlates meaningfully with generated sample quality, addressing the notorious mode collapse and vanishing gradient problems of standard GANs. |
| ScholarGateConjunt de dades ↗ |
|
|