手法を比較
選択した手法を並べて確認できます。異なる行はハイライト表示されます。
| Wasserstein GAN (WGAN)× | 拡散モデル× | |
|---|---|---|
| 分野 | 深層学習 | 深層学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 2017 | 2020 |
| 提唱者≠ | Martín Arjovsky, Soumith Chintala & Léon Bottou | Ho, J., Jain, A. & Abbeel, P. |
| 種類≠ | Generative adversarial network variant | Generative deep learning (denoising diffusion) |
| 原典≠ | Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223. link ↗ | Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS. link ↗ |
| 別名≠ | WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN | Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM |
| 関連≠ | 3 | 4 |
| 概要≠ | 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. | A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling. |
| ScholarGateデータセット ↗ |
|
|