Сравнение методов

	Доменно-адаптивный ГАН	Полусупервизорная GAN
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2016–2017	2016
Автор метода	Ganin et al. (DANN); Zhu et al. (CycleGAN)	Odena, A.; Salimans, T. et al.
Тип	Generative adversarial model with domain adaptation	Semi-supervised generative model
Основополагающий источник	Ganin, Y., Ustunova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59), 1–35.	Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29.
Другие названия	DA-GAN, domain adaptation GAN, adversarial domain adaptation, domain-adaptive generative adversarial network	SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning
Связанные	6	5
Сводка	A Domain-Adaptive GAN combines generative adversarial learning with domain adaptation to bridge the distribution gap between a labeled source domain and an unlabeled or sparsely labeled target domain. By training a generator and discriminator adversarially, the model learns domain-invariant representations or translated samples, enabling a classifier or detector trained on source data to generalize effectively to the target domain without requiring abundant target labels.	Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples.