# Bioinspired CNNs for border completion in occluded images

arXiv: https://arxiv.org/abs/2603.10694 · HTML: https://mlsanity.com/paper/2603.10694/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 24 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 2 of 2)

- [A rotation-equivariant convolutional neural network model of primary visual cortex](https://mlsanity.com/paper/1809.10504/) (2018)
- [Enhancing CNNs robustness to occlusions with bioinspired filters for border completion](https://mlsanity.com/paper/2504.17619/) (2025)

## Abstract (arXiv)

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 demonstrates improved performance, with gains varying depending on the severity of the occlusions and the dataset.