Work

Adversarial Noise Layer: Regularize Neural Network by Adding Noise

Year: 2019
Type: conference-paper
Abstract: In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL), which are able to significantly improve CNN's generalization ability by adding carefully crafted noise into the intermediate layer activations. ANL can be easily implemented and integrated with most of the mainstream CNN-based models. We compared the effects of the different types of noise and visually demonstrate that our proposed adversarial noise instruct CNN models to learn to extract cleaner feature maps, which further reduce the risk of over-fitting. We also conclude that models trained with ANL are more robust to the adversarial examples generated by FGSM than the traditional adversarial training approaches.
Language: English
Open Access status: green
OpenAlex ID: W2971018118
FWCI: 3.429
Cites: 27
Cited by: 103
Related to: 10