Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection

Published: 26 Apr 2024, Last Modified: 15 Jul 2024UAI 2024 oralEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Failure Recognition, Object Detection, Uncertainty Estimation, Autonomous Driving, Cost-Sensitive Framework, Safety
TL;DR: This paper presents a cost-sensitive framework for object detection, integrating optimized failure recognition based on uncertainty and enhancing safety and performance across three autonomous driving datasets.
Abstract: Object detectors in real-world applications often fail to detect objects due to varying factors such as weather conditions and noisy input. Therefore, a process that mitigates false detections is crucial for both safety and accuracy. While uncertainty-based thresholding shows promise, previous works demonstrate an imperfect correlation between uncertainty and detection errors. This hinders ideal thresholding, prompting us to further investigate the correlation and associated cost with different types of uncertainty. We therefore propose a cost-sensitive framework for object detection tailored to user-defined budgets on the two types of errors, missing and false detections. We derive minimum thresholding requirements to prevent performance degradation and define metrics to assess the applicability of uncertainty for failure recognition. Furthermore, we automate and optimize the thresholding process to maximize the failure recognition rate w.r.t. the specified budget. Evaluation on three autonomous driving datasets demonstrates that our approach significantly enhances safety, particularly in challenging scenarios. Leveraging localization aleatoric uncertainty and softmax-based entropy only, our method boosts the failure recognition rate by 36-60\% compared to conventional approaches. Code is available at https://mos-ks.github.io/publications.
List Of Authors: Kassem-Sbeyti, Moussa and Karg, Michelle and Wirth, Christian and Klein, Nadja and Albayrak, Sahin
Latex Source Code: zip
Signed License Agreement: pdf
Code Url: https://mos-ks.github.io/publications
Submission Number: 176
Loading