AI RESEARCH
Bioinspired CNNs for border completion in occluded images
arXiv CS.CV
•
ArXi:2603.10694v1 Announce Type: new We exploit the mathematical modeling of the border completion problem in the visual cortex to design convolutional neural network (CNN) filters that enhance robustness to image occlusions. We evaluate our CNN architecture, BorderNet, on three occluded datasets (MNIST, Fashion-MNIST, and EMNIST) under two types of occlusions: stripes and grids. In all cases, BorderNet nstrates improved performance, with gains varying depending on the severity of the occlusions and the dataset.