Сравнение методов

	Доменно-адаптивный ГАН	Генеративно-состязательная сеть
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2016–2017	2014
Автор метода	Ganin et al. (DANN); Zhu et al. (CycleGAN)	Goodfellow, I. et al.
Тип	Generative adversarial model with domain adaptation	Generative deep learning (adversarial two-network game)
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.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
Другие названия	DA-GAN, domain adaptation GAN, adversarial domain adaptation, domain-adaptive generative adversarial network	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Связанные	6	4
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.	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.