A Theoretical and Practical Framework for Evaluating Uncertainty Calibration in Object Detection

arXiv:2309.00464v2 Announce Type: replace
Abstract: The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains, making the problem of uncertainty calibration pivotal when considering the future of deep learning. This is especially true when considering object detection systems, that are commonly present in safety-critical applications such as autonomous driving, robotics and medical diagnosis. For this reason, this …

abstract applications arxiv cs.ai cs.cv demand detection domains framework learning systems machine machine learning making networks neural networks object pivotal practical systems type uncertainty world