Invited Talk: Toward Trustworthy, Human-Aligned Vision (Dr. Dario Zanca, FAU Erlangen-Nuremberg)

#CIS_Chapter #CIS_Germany #computational-intelligence #machine-learning #human-aligned-vision #trustworthy-computer-vision #model-evidence-stability
Share

Vision models now match or exceed human accuracy on many benchmarks, yet they can fail for the “wrong reasons”: brittle decision boundaries, attention that diverges from human strategies, and invariances that do not reflect perception. In this talk, I present a unified research program toward trustworthy, human-aligned vision, organized around a simple question: what does a model treat as evidence, and how stable is that evidence under change?


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • Department Artificial Intelligence in Biomedical Engineering (AIBE), FAU Erlangen-Nuremberg
  • Nuernberger Str. 74
  • Erlangen, Bayern
  • Germany 91052
  • Room Number: 00.014 (Seminarraum 1), EG
  • Contact Event Host
  • Starts 27 February 2026 01:00 PM UTC
  • Ends 26 March 2026 08:00 AM UTC
  • No Admission Charge

  Speakers

Dr. Dario Zanca

Topic:

Toward Trustworthy, Human-Aligned Vision

Vision models now match or exceed human accuracy on many benchmarks, yet they can fail for the “wrong reasons”: brittle decision boundaries, attention that diverges from human strategies, and invariances that do not reflect perception. In this talk, I present a unified research program toward trustworthy, human-aligned vision, organized around a simple question: what does a model treat as evidence, and how stable is that evidence under change?

Biography:

Dario Zanca obtained a Bachelor's and Master's degree in Mathematics from the University of Palermo, Italy. He later obtained his PhD from the Universities of Florence and Siena, Italy, where he focused on machine learning and visual attention modeling. He was a visiting researcher at various institutions including Caltech in California, USA, and Universidad de Santiago de Compostela in Spain.

Currently, he is a Postdoc researcher and Head of the Applied Machine Learning group at Friedrich-Alexander-Universität Erlangen-Nürnberg in Germany. His research interests broadly fall into the areas of deep learning and computational cognitive sciences, with a focus on human-inspired computer vision and robustness.