Adversarial Noise Layer: Regularize Neural Network By Adding Noise
share
In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL), which significantly improve the CNN's generalization ability by adding adversarial noise in the hidden layers. ANL is easy to implement and can be integrated with most of the CNN-based models. We compared the impact of the different type of noise and visually demonstrate that adversarial noise guide CNNs to learn to extract cleaner feature maps, further reducing the risk of over-fitting. We also conclude that the model trained with ANL is more robust to FGSM and IFGSM attack. Code is available at: https://github.com/youzhonghui/ANL
READ FULL TEXT