Adversarial Dropout for Supervised and Semi-supervised Learning

Autor:	Park, Sungrae, Park, Jun-Keon, Shin, Su-Jin, Moon, Il-Chul
Rok vydání:	2017
Předmět:	Computer Science - Learning Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually biased inputs to enhance the generality, this paper introduces adversarial dropout, which is a minimal set of dropouts that maximize the divergence between the outputs from the network with the dropouts and the training supervisions. The identified adversarial dropout are used to reconfigure the neural network to train, and we demonstrated that training on the reconfigured sub-network improves the generalization performance of supervised and semi-supervised learning tasks on MNIST and CIFAR-10. We analyzed the trained model to reason the performance improvement, and we found that adversarial dropout increases the sparsity of neural networks more than the standard dropout does. Comment: submitted to AAAI-18
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1707.03631 Zobrazit plný text záznamu View this record from Arxiv