Arlindo L. Oliveira

Full Professor, Instituto Superior Técnico

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

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

#2015 · Lucas Piper, Arlindo L. Oliveira, Tiago Marques

We introduce Early Vision Networks (EVNets), hybrid CNNs combining biologically inspired subcortical and cortical front-end blocks, which improve V1 alignment and significantly boost robustness to different image perturbations.