Porovnat metody

	Vícevrstvý perceptron adaptivní na doménu	Doménově adaptivní konvoluční neuronová síť
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2006–2016	2015–2017
Tvůrce	Ben-David et al.; Ganin et al.	Ganin, Y. & Lempitsky, V. (domain-adversarial framework); Tzeng et al. (ADDA)
Typ	Domain adaptation of feedforward neural network	Domain-adaptive deep learning model
Původní zdroj	Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010). A theory of learning from different domains. Machine Learning, 79(1–2), 151–175.	Ganin, Y., Ustinova, 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.
Další názvy	DA-MLP, domain-adaptive MLP, domain-adapted feedforward network, domain adaptation with MLP	DA-CNN, domain adaptation CNN, domain-adaptive deep convolutional network, CNN with domain adaptation
Příbuzné	5	5
Shrnutí	A domain-adaptive multilayer perceptron (DA-MLP) is a feedforward neural network trained to learn representations that are useful across a labeled source domain and an unlabeled or differently distributed target domain. By minimizing both a task loss and a domain-discrepancy objective, the MLP generalizes to the target domain with little or no target-domain labels.	A domain-adaptive CNN trains a convolutional network on a labeled source domain and adapts its learned feature representations to an unlabeled or lightly labeled target domain, bridging the distribution gap so that visual classifiers transfer reliably across datasets, sensors, or imaging conditions without full re-annotation.