方法对比

	CycleGAN：具有循环一致性的非配对图像到图像翻译	生成对抗网络	瓦瑟施泰因生成对抗网络 (WGAN)
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2017	2014	2017
提出者	Jun-Yan Zhu et al.	Goodfellow, I. et al.	Martín Arjovsky, Soumith Chintala & Léon Bottou
类型	Unsupervised image-to-image translation	Generative deep learning (adversarial two-network game)	Generative adversarial network variant
开创性文献	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.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223.
别名	Cycle-Consistent Adversarial Networks, Unpaired Image-to-Image Translation, Cycle-GAN, Çevrimsel Tutarlı GAN	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN
相关	3	4	3
摘要	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.	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.	Wasserstein GAN (WGAN) is a generative adversarial network variant introduced by Arjovsky, Chintala, and Bottou in 2017 that replaces the Jensen-Shannon divergence used in the original GAN with the Wasserstein-1 (Earth Mover) distance. This substitution provides a theoretically grounded training objective that yields more stable optimization and a loss value that correlates meaningfully with generated sample quality, addressing the notorious mode collapse and vanishing gradient problems of standard GANs.