Re:Feature Visualization: How neural nets build up their und...
by michaf on Friday November 10, 2017 @01:58PM
(#15672048)
The article mentions pooling layers as one source for the high frequency patterns. Jeffrey Hinton recently introduced capsule networks (https://news.ycombinator.com/item?id=15609402), in part because he wants to get rid of pooling layers. Maybe this approach is effective to counter (at least visually indistinguishable) adversarial examples.
edit: ok, someone already tested it, and it does not seem to help that much: https://github.com/jaesik817/adv_attack_capsnet