Сравнение на методи

	Генеративни състезателни мрежи с трансферно обучение (Transfer Learning GAN)	Трансферно обучение с конволюционна невронна мрежа
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2014–2018	2010–2014
Създател	Goodfellow, I. et al. (GAN); Wang & Ramanan (transfer to GAN)	Pan, S. J. & Yang, Q. (transfer learning framework); popularized for CNNs by Yosinski et al. and Razavian et al.
Тип	Generative model with transferred weights	Transfer learning applied to convolutional neural networks
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.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Други названия	TL-GAN, pretrained GAN, GAN fine-tuning, domain-adaptive GAN	TL-CNN, pretrained CNN, CNN fine-tuning, feature-extracting CNN
Свързани	6	4
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.	Transfer Learning with CNN reuses a convolutional neural network that has already been trained on a large dataset — most commonly ImageNet — and adapts its learned feature detectors to a new, often smaller target dataset. This lets researchers achieve strong image-recognition performance without the massive compute and data resources required to train a CNN from scratch.