Сравнение на методи

	Невронен пренос на стил	Генеративна състезателна мрежа	Трансферно обучение
Област	Дълбоко обучение	Дълбоко обучение	Машинно обучение
Семейство	Machine learning	Machine learning	Machine learning
Година на възникване	2015	2014	2010 (formalized); 1990s (early roots)
Създател	Gatys, L. A.; Ecker, A. S.; Bethge, M.	Goodfellow, I. et al.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Iterative optimization over CNN feature statistics	Generative deep learning (adversarial two-network game)	Learning paradigm
Основополагащ източник	Gatys, L. A., Ecker, A. S., & Bethge, M. (2016). Image Style Transfer Using Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2414–2423.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Други названия	NST, artistic style transfer, neural artistic style, CNN style transfer	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Свързани	3	4	3
Резюме	Neural Style Transfer (NST) is a deep-learning image synthesis technique, introduced by Gatys, Ecker, and Bethge in 2015, that separates the semantic content of one image from the visual texture and artistic style of another, then recombines them into a single synthesized image by iteratively optimizing pixel values to minimize a combined content and style loss computed from the feature maps of a pretrained convolutional neural network.	A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.