Picture for Aneeqa Merhab

Aneeqa Merhab

Enhancing CNNs robustness to occlusions with bioinspired filters for border completion

Add code
Apr 24, 2025
Catarina P. Coutinho, Aneeqa Merhab, Janko Petkovic, Ferdinando Zanchetta, Rita Fioresi
Figure 1 for Enhancing CNNs robustness to occlusions with bioinspired filters for border completion
Figure 2 for Enhancing CNNs robustness to occlusions with bioinspired filters for border completion
Figure 3 for Enhancing CNNs robustness to occlusions with bioinspired filters for border completion
Figure 4 for Enhancing CNNs robustness to occlusions with bioinspired filters for border completion

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.

* Submitted to the 7th International Conference on Geometric Science of Information 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon