Comparar métodos
Examine os métodos selecionados lado a lado; as linhas que diferem ficam destacadas.
| Wasserstein GAN (WGAN)× | CycleGAN: Tradução de Imagens Não Pareadas com Consistência Cíclica× | |
|---|---|---|
| Área | Aprendizado profundo | Aprendizado profundo |
| Família | Machine learning | Machine learning |
| Ano de origem | 2017 | 2017 |
| Autor original≠ | Martín Arjovsky, Soumith Chintala & Léon Bottou | Jun-Yan Zhu et al. |
| Tipo≠ | Generative adversarial network variant | Unsupervised image-to-image translation |
| Fonte seminal≠ | Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223. link ↗ | Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE International Conference on Computer Vision (ICCV), 2242–2251. DOI ↗ |
| Outros nomes | WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN | Cycle-Consistent Adversarial Networks, Unpaired Image-to-Image Translation, Cycle-GAN, Çevrimsel Tutarlı GAN |
| Relacionados | 3 | 3 |
| Resumo≠ | 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. | CycleGAN, introduced by Zhu et al. at ICCV 2017, learns to translate images between two visual domains without requiring paired training examples. It trains two generators and two discriminators simultaneously, enforcing a cycle-consistency constraint so that an image translated from domain X to Y and back again recovers the original. This makes it applicable whenever large aligned datasets are unavailable, such as converting photographs to artwork styles, turning summer landscapes into winter scenes, or mapping satellite imagery to map tiles. |
| ScholarGateConjunto de dados ↗ |
|
|