Re:Slight Street Sign Modifications Can Fool Machine Learnin...
by bitL on Saturday August 05, 2017 @08:44AM
(#14935431)
Alright, so this is an image augmentation problem. Another training set with white noise variations, random unrelated pixellation/overlay texts can solve this. Simply your training wasn't general enough.
[ Parent
| on HN ]
Re:Slight Street Sign Modifications Can Fool Machine Learnin...
by visarga on Saturday August 05, 2017 @09:27AM
(#14935557)
Constructing adversarial examples is a sophisticated task, but it's being done.
Re:Slight Street Sign Modifications Can Fool Machine Learnin...
by bitL on Saturday August 05, 2017 @09:34AM
(#14935587)
Sure, and it should go hand in hand with appropriate image augmentation. Maybe make something like a GAN that would try to generate anti-obfuscation image augmentation for every new adversarial example...?
Our eyes can be fooled easily anyway.