Sammenlign metoder

	Finjustert generativt antagonistisk nettverk	Finetunet konvolusjonelt nevralt nettverk
Fagfelt	Dyp læring	Dyp læring
Familie	Machine learning	Machine learning
Opprinnelsesår	2014 (GAN); 2019–2020 (fine-tuning paradigm)	2012–2014
Opphavsperson	Goodfellow, I. et al. (GAN); fine-tuning practice established ~2019–2020	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Type	Generative model (adversarial training + transfer)	Transfer learning technique (supervised fine-tuning)
Opprinnelig kilde	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.	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	Fine-Tuned GAN, GAN Fine-Tuning, Domain-Adapted GAN, Transfer GAN	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Relaterte	6	5
Sammendrag	A Fine-Tuned GAN starts from a large pre-trained generative adversarial network and continues adversarial training on a smaller target dataset, allowing the model to synthesize high-quality samples in a new domain without training from scratch. This transfer approach dramatically reduces data and compute requirements while preserving the rich feature representations learned during pre-training.	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.