Position Paper: On the Role of Abductive Reasoning in Semantic Image Segmentation

   page       BibTeX_logo.png       attach   
Andrea Rafanelli, Stefania Costantini, Andrea Omicini
Agostino Dovier, Angelo Montanari, Andrea Orlandini (eds.)
AIxIA 2022 Discussion Papers, chapter 9, pages 75–84
CEUR Workshop Proceedings (AIxIA Series) 3419
Sun SITE Central Europe, RWTH Aachen University, Aachen, Germany
June 2023

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.

keywordsneuro-symbolic, abductive reasoning, semantic segmentation, XAI
reference talk
page_white_powerpointOn the role of abductive reasoning in semantic image segmentation (AIxIA 2022, 02/12/2022) — Andrea Rafanelli (Andrea Rafanelli, Stefania Costantini, Andrea Omicini)
origin event
journal or series
book CEUR Workshop Proceedings (CEUR-WS.org)
funding project
wrenchEXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)
works as
reference publication for talk
page_white_powerpointOn the role of abductive reasoning in semantic image segmentation (AIxIA 2022, 02/12/2022) — Andrea Rafanelli (Andrea Rafanelli, Stefania Costantini, Andrea Omicini)