Сравнение на методи

	Генеративни състезателни мрежи с трансферно обучение (Transfer Learning GAN)	Домейн-адаптивен GAN
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2014–2018	2016–2017
Създател	Goodfellow, I. et al. (GAN); Wang & Ramanan (transfer to GAN)	Ganin et al. (DANN); Zhu et al. (CycleGAN)
Тип	Generative model with transferred weights	Generative adversarial model with domain adaptation
Основополагащ източник	Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems (NeurIPS), 27, 2672–2680.	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.
Други названия	TL-GAN, pretrained GAN, GAN fine-tuning, domain-adaptive GAN	DA-GAN, domain adaptation GAN, adversarial domain adaptation, domain-adaptive generative adversarial network
Свързани	6	6
Резюме	Transfer Learning GAN initialises a Generative Adversarial Network — or both its generator and discriminator — from weights pretrained on a large source dataset, then fine-tunes the network on a smaller target dataset. This approach allows high-quality generative modelling even when target-domain data are scarce, by reusing low- and mid-level feature representations learned at scale.	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.