Bioinspired CNNs for border completion in occluded images

Catarina P. Coutinho, Aneeqa Merhab, Janko Petkovic, Ferdinando Zanchetta, Rita Fioresi
3/11/2026
cs.CV

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Improving Classification of Occluded Objects through Scene Context

84% match2025

Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?

83% match2024

Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness

81% match2 repos32024

A Brain-Inspired Regularizer for Adversarial Robustness

80% match1 repo12024

Convolution goes higher-order: a biologically inspired mechanism empowers image classification

79% match2024

OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks

78% match2023

Cite this paper

@article{coutinho2026bioinspired,
  title  = {Bioinspired CNNs for border completion in occluded images},
  author = {Catarina P. Coutinho and Aneeqa Merhab and Janko Petkovic and Ferdinando Zanchetta and Rita Fioresi},
  year   = {2026},
  eprint = {2603.10694},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.10694v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.10694.svg)](https://codeofpaper.com/paper/2603.10694)

Discussion