Uporedite metode

	Невронски пренос стила	Generativna suparnička mreža	Transferno učenje	Varijacioni autoenkoder
Oblast	Duboko učenje	Duboko učenje	Mašinsko učenje	Duboko učenje
Porodica	Machine learning	Machine learning	Machine learning	Machine learning
Godina nastanka	2015	2014	2010 (formalized); 1990s (early roots)	2014
Tvorac	Gatys, L. A.; Ecker, A. S.; Bethge, M.	Goodfellow, I. et al.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)	Kingma, D. P. & Welling, M.
Tip	Iterative optimization over CNN feature statistics	Generative deep learning (adversarial two-network game)	Learning paradigm	Deep generative latent-variable model (encoder–decoder)
Temeljni izvor	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.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Drugi nazivi	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	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Srodne	3	4	3	5
Sažetak	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.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.