Adversarial Dropout for Supervised and Semi-Supervised LearningAdversarial Dropout for Supervised and Semi-Supervised LearningPark, Sungrae and Park, Jun-Keon and Shin, Su-Jin and Moon, Il-Chul2018
Paper summarydavidstutzPark et al. introduce adversarial dropout, a variant of adversarial training based on adversarially computing dropout masks. Specifically, instead of training on adversarial examples, the authors propose an efficient method to compute adversarial dropout masks during training. In experiments, this approach seems to improve generalization performance in semi-supervised settings.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).