Understanding-Live-Programming-Environments-Integrating-Cross-Cutting-Perspectives

Efficient-Deep-Autoencoders-for-Multivariate-Time-Series-Anomaly-Detection

Distributed-MIMO-Measurements-for-Integrated-Communication-and-Sensing-in-an-Industrial-Environment

Bayesian-Method-for-Constraint-Inference-from-User-Demonstrations-Based-on-Preference-Models

Challenges-and-Opportunities-in-Federated-Unlearning-A-Comprehensive-Analysis

Influence-of-Architecture-on-Pre-trained-Language-Models

Unveiling-the-Risks-of-Free-Proxies-A-Detailed-Analysis

Root-Causing-Prediction-Anomalies-Using-Explainable-AI-A-Detailed-Analysis


A cost-sensitive framework for object detection that leverages uncertainty quantification to enhance safety and reliability by selectively discarding unreliable detections.


coremsg

enhancing-safety-and-reliability-of-object-detectors-through-cost-sensitive-uncertainty-based-failure-recognition


Enhancing Safety and Reliability of Object Detectors through Cost-Sensitive Uncertainty-Based Failure Recognition


title_rewrite

Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection