mlsanityData to 14 Oct 2026

Enhancing CNNs robustness to occlusions with bioinspired filters for border completion

arXiv 2504.17619 ↗First posted 24 Apr 2025cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 3 of its 26 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

3 of 26 references.

References · 3

  1. 2017Normative theory of visual receptive fieldscited by 15
  2. 2023Leveraging dendritic properties to advance machine learning and neuro-inspired computingcited by 6
  3. 2015Random wiring, ganglion cell mosaics, and the functional architecture of the visual cortexcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Bioinspired CNNs for border completion in occluded imagescited by 0