Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| CycleGAN: Tafsiri ya Picha-kwa-Picha isiyo na Jozi yenye Utaratibu wa Mzunguko× | Wasserstein GAN (WGAN)× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili | 2017 | 2017 |
| Mwanzilishi≠ | Jun-Yan Zhu et al. | Martín Arjovsky, Soumith Chintala & Léon Bottou |
| Aina≠ | Unsupervised image-to-image translation | Generative adversarial network variant |
| Chanzo asilia≠ | 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 ↗ | Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223. link ↗ |
| Majina mbadala | Cycle-Consistent Adversarial Networks, Unpaired Image-to-Image Translation, Cycle-GAN, Çevrimsel Tutarlı GAN | WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN |
| Zinazohusiana | 3 | 3 |
| Muhtasari≠ | 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. | 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. |
| ScholarGateSeti ya data ↗ |
|
|