Position paper: On the role of abductive reasoning in semantic image segmentation


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Andrea Rafanelli, Stefania Costantini, Andrea Omicini

This position paper provides insights aiming at resolving the most pressing needs and issues of computer vision algorithms. Specifically, these problems relate to the scarcity of data, the inability of such algorithms to adapt to never-seen-before conditions, and the challenge of developing explainable and trustworthy algorithms.
This work proposes the incorporation of reasoning systems, and in particular of abductive reasoning, into image segmentation algorithms as a potential solution to the aforementioned issues.

(keywords)  neuro-symbolic, abductive reasoning, semantic segmentation, XAI

Talks

Events

  • 21th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022) — 28/11/2022–02/12/2022

Publication

— authors

Andrea Rafanelli, Stefania Costantini, Andrea Omicini

— status

camera-ready sent

— sort

paper in proceedings

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY