Google & Johns Hopkins University | Can Adversarial Examples Improve Image Recognition? | Synced
Rather than attempting to defend convolutional networks against them, the researchers introduce a novel enhanced adversarial training scheme, AdvProp, which treats adversarial examples as additiona...
Source: Synced | AI Technology & Industry Review
Rather than attempting to defend convolutional networks against them, the researchers introduce a novel enhanced adversarial training scheme, AdvProp, which treats adversarial examples as additional training examples to improve the accuracy of image classification models.