Stylized Adversarial Defense

Muzammal Naseer
Muzammal Naseer
Salman Khan
Salman Khan
Munawar Hayat
Munawar Hayat
Cited by: 0|Bibtex|Views9|Links

Abstract:

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to robustify the model. In contrast to existing adversarial training methods that only use class-bounda...More

Code:

Data:

Your rating :
0

 

Tags
Comments