Sammenlign metoder

	Domæneadaptiv GAN	Transfer Learning GAN
Fagområde	Dyb læring	Dyb læring
Familie	Machine learning	Machine learning
Oprindelsesår	2016–2017	2014–2018
Ophavsperson	Ganin et al. (DANN); Zhu et al. (CycleGAN)	Goodfellow, I. et al. (GAN); Wang & Ramanan (transfer to GAN)
Type	Generative adversarial model with domain adaptation	Generative model with transferred weights
Oprindelig kilde	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., 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.
Aliasser	DA-GAN, domain adaptation GAN, adversarial domain adaptation, domain-adaptive generative adversarial network	TL-GAN, pretrained GAN, GAN fine-tuning, domain-adaptive GAN
Relaterede	6	6
Resumé	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.	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.