方法对比

	自监督生成对抗网络	Semi-supervised GAN
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2019	2016
提出者	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N.	Odena, A.; Salimans, T. et al.
类型	Generative model with self-supervised auxiliary tasks	Semi-supervised generative model
开创性文献	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. (2019). Self-Supervised GANs via Auxiliary Rotation Loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12154–12163.	Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29.
别名	SS-GAN, Self-supervised GAN, Self-supervised Generative Adversarial Network, GAN with self-supervised auxiliary tasks	SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning
相关	5	5
摘要	Self-supervised GAN augments a standard Generative Adversarial Network with one or more self-supervised auxiliary tasks — such as predicting image rotation or patch position — that stabilise adversarial training and yield a discriminator that learns rich, transferable representations from unlabeled data without requiring manual annotations.	Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples.