Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Pašuzraudzības GAN× | Generatīvais Adversariālais Tīkls× | |
|---|---|---|
| Nozare | Dziļā mācīšanās | Dziļā mācīšanās |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2019 | 2014 |
| Autors≠ | Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. | Goodfellow, I. et al. |
| Tips≠ | Generative model with self-supervised auxiliary tasks | Generative deep learning (adversarial two-network game) |
| Pirmavots≠ | Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. (2019). Self-Supervised GANs via Auxiliary Rotation Loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12154–12163. link ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ |
| Citi nosaukumi | SS-GAN, Self-supervised GAN, Self-supervised Generative Adversarial Network, GAN with self-supervised auxiliary tasks | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network |
| Saistītās≠ | 5 | 4 |
| Kopsavilkums≠ | Self-supervised GAN augments a standard Generative Adversarial Network with one or more self-supervised auxiliary tasks — such as predicting image rotation or patch position — that stabilise adversarial training and yield a discriminator that learns rich, transferable representations from unlabeled data without requiring manual annotations. | 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. |
| ScholarGateDatu kopa ↗ |
|
|