Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises. (arXiv:2206.07282v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07282

Compared to human vision, computer vision based on convolutional neural
networks (CNN) are more vulnerable to adversarial noises. This difference is
likely attributable to how the eyes sample visual input and how the brain
processes retinal samples through its dorsal and ventral visual pathways, which
are under-explored for computer vision. Inspired by the brain, we design
recurrent neural networks, including an input sampler that mimics the human
retina, a dorsal network that guides where to look next, and a ventral …

arxiv cv human networks neural neural networks