Vertaile menetelmiä

	CycleGAN: Parittomien kuvien välinen käännös syklinmukaisuudella	Neuraalinen tyylinsiirto
Tieteenala	Syväoppiminen	Syväoppiminen
Menetelmäperhe	Machine learning	Machine learning
Syntyvuosi	2017	2015
Kehittäjä	Jun-Yan Zhu et al.	Gatys, L. A.; Ecker, A. S.; Bethge, M.
Tyyppi	Unsupervised image-to-image translation	Iterative optimization over CNN feature statistics
Alkuperäislähde	Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE International Conference on Computer Vision (ICCV), 2242–2251.	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.
Rinnakkaisnimet	Cycle-Consistent Adversarial Networks, Unpaired Image-to-Image Translation, Cycle-GAN, Çevrimsel Tutarlı GAN	NST, artistic style transfer, neural artistic style, CNN style transfer
Liittyvät	3	3
Tiivistelmä	CycleGAN, introduced by Zhu et al. at ICCV 2017, learns to translate images between two visual domains without requiring paired training examples. It trains two generators and two discriminators simultaneously, enforcing a cycle-consistency constraint so that an image translated from domain X to Y and back again recovers the original. This makes it applicable whenever large aligned datasets are unavailable, such as converting photographs to artwork styles, turning summer landscapes into winter scenes, or mapping satellite imagery to map tiles.	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.