An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks(https://arxiv.org/pdf/1702.02382.pdf, 8 Feb 2017),这篇文章中使用对抗网络来做图像分割的半监督学习。半监督学习中一部分数据有标记,而另一部分数据无标记,可以在准备训练数据的过程中节省大量的人力物力。
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (https://arxiv.org/abs/1609.04802, 21 Nov, 2016)这篇文章将对抗学习用于基于单幅图像的高分辨重建。基于深度学习的高分辨率图像重建已经取得了很好的效果,其方法是通过一系列低分辨率图像和与之对应的高分辨率图像作为训练数据,学习从低分辨率图像到高分辨率图像的映射函数,这函数通过卷积神经网络来表示。
[1] Goodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. "Generative adversarial nets." In Advances in neural information processing systems, pp. 2672-2680. 2014.
[2] Luc, Pauline, Camille Couprie, Soumith Chintala, and Jakob Verbeek. "Semantic Segmentation using Adversarial Networks." arXiv preprint arXiv:1611.08408 (2016).
[3] Mateusz Koziński, Loïc Simon, Frédéric Jurie, "An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks", arXiv preprint arXiv:1702.02382(2017).
[4] Hoffman, Judy, Dequan Wang, Fisher Yu, and Trevor Darrell. "FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation." arXiv preprint arXiv:1612.02649 (2016).
[5] Ledig, Christian, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken et al. "Photo-realistic single image super-resolution using a generative adversarial network." arXiv preprint arXiv:1609.04802 (2016).