Leveraging the Human Ventral Visual Stream to Improve Neural Network Robustness

arXiv:2405.02564v1 Announce Type: new
Abstract: Human object recognition exhibits remarkable resilience in cluttered and dynamic visual environments. In contrast, despite their unparalleled performance across numerous visual tasks, Deep Neural Networks (DNNs) remain far less robust than humans, showing, for example, a surprising susceptibility to adversarial attacks involving image perturbations that are (almost) imperceptible to humans. Human object recognition likely owes its robustness, in part, to the increasingly resilient representations that emerge along the hierarchy of the ventral visual cortex. Here …

abstract adversarial adversarial attacks arxiv attacks contrast cs.ai cs.cv dynamic environments example human humans image network networks neural network neural networks object performance q-bio.nc recognition resilience robust robustness tasks type visual