Sammenlign metoder

	Domene-adaptiv konvolusjonelt nevralt nettverk	Finetunet konvolusjonelt nevralt nettverk
Fagfelt	Dyp læring	Dyp læring
Familie	Machine learning	Machine learning
Opprinnelsesår	2015–2017	2012–2014
Opphavsperson	Ganin, Y. & Lempitsky, V. (domain-adversarial framework); Tzeng et al. (ADDA)	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Type	Domain-adaptive deep learning model	Transfer learning technique (supervised fine-tuning)
Opprinnelig kilde	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.	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.
Alias	DA-CNN, domain adaptation CNN, domain-adaptive deep convolutional network, CNN with domain adaptation	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Relaterte	5	5
Sammendrag	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.	Fine-tuning a CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch.