Saved in:
Bibliographic Details
Main Authors: Polavaram, Sridevi, Zhou, Xin, Ravi, Meenu, Zarei, Mohammad, Srivastava, Anmol
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915253706555392
author Polavaram, Sridevi
Zhou, Xin
Ravi, Meenu
Zarei, Mohammad
Srivastava, Anmol
author_facet Polavaram, Sridevi
Zhou, Xin
Ravi, Meenu
Zarei, Mohammad
Srivastava, Anmol
contents Vision systems are increasingly deployed in critical domains such as surveillance, law enforcement, and transportation. However, their vulnerabilities to rare or unforeseen scenarios pose significant safety risks. To address these challenges, we introduce Context-Awareness and Interpretability of Rare Occurrences (CAIRO), an ontology-based human-assistive discovery framework for failure cases (or CP - Critical Phenomena) detection and formalization. CAIRO by design incentivizes human-in-the-loop for testing and evaluation of criticality that arises from misdetections, adversarial attacks, and hallucinations in AI black-box models. Our robust analysis of object detection model(s) failures in automated driving systems (ADS) showcases scalable and interpretable ways of formalizing the observed gaps between camera perception and real-world contexts, resulting in test cases stored as explicit knowledge graphs (in OWL/XML format) amenable for sharing, downstream analysis, logical reasoning, and accountability.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context-Awareness and Interpretability of Rare Occurrences for Discovery and Formalization of Critical Failure Modes
Polavaram, Sridevi
Zhou, Xin
Ravi, Meenu
Zarei, Mohammad
Srivastava, Anmol
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Vision systems are increasingly deployed in critical domains such as surveillance, law enforcement, and transportation. However, their vulnerabilities to rare or unforeseen scenarios pose significant safety risks. To address these challenges, we introduce Context-Awareness and Interpretability of Rare Occurrences (CAIRO), an ontology-based human-assistive discovery framework for failure cases (or CP - Critical Phenomena) detection and formalization. CAIRO by design incentivizes human-in-the-loop for testing and evaluation of criticality that arises from misdetections, adversarial attacks, and hallucinations in AI black-box models. Our robust analysis of object detection model(s) failures in automated driving systems (ADS) showcases scalable and interpretable ways of formalizing the observed gaps between camera perception and real-world contexts, resulting in test cases stored as explicit knowledge graphs (in OWL/XML format) amenable for sharing, downstream analysis, logical reasoning, and accountability.
title Context-Awareness and Interpretability of Rare Occurrences for Discovery and Formalization of Critical Failure Modes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2504.16117