paper-with-me

홈 › Papers

Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection

2024-04-26 · Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth, Nadja Klein, Sahin Albayrak

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.

📄 PDF Abstract BibTeX arXiv:2404.17427

Code (1)

continental/uncertainty-detection-autolabeling 공식 구현 tf

Tasks

Autonomous DrivingObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Identifying Incorrect Classifications with Balanced Uncertainty

2021-10-15 · Bolian Li, Zige Zheng, Changqing Zhang

Uncertainty estimation is critical for cost-sensitive deep-learning applications (i.e. disease diagnosis). It is very challenging partly due to the inaccessibility of uncertainty groundtruth in most datasets. Previous wo…

Out of Distribution (OOD) Detection

Explainable bank failure prediction models: Counterfactual explanations to reduce the failure risk

2024-07-14 · Seyma Gunonu, Gizem Altun, Mustafa Cavus

The accuracy and understandability of bank failure prediction models are crucial. While interpretable models like logistic regression are favored for their explainability, complex models such as random forest, support ve…

counterfactualCounterfactual Explanation

Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation

2016-11-16 · Yu-An Chung, Shao-Wen Yang, Hsuan-Tien Lin

While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-w…

ClassificationDeep LearningGeneral ClassificationObject Recognition

One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning

2022-11-30 · NeurIPS 2023 11 · Marc Rigter, Bruno Lacerda, Nick Hawes

Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk o…

AllDecision MakingOffline RLReinforcement Learning (RL)+1

RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes

2024-05-07 · Kyle Stachowicz, Sergey Levine

Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints a…

reinforcement-learningReinforcement Learning