← all papers · overview

Enhancing CNNs robustness to occlusions with bioinspired filters for border completion

Abstract

We exploit the mathematical modeling of the visual cortex mechanism for border completion to define custom filters for CNNs. We see a consistent improvement in performance, particularly in accuracy, when our modified LeNet 5 is tested with occluded MNIST images.

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).