Uncertainty Quantification and Label Error Detection

This lecture by the instructor covers the topics of uncertainty quantification and label error detection for semantic segmentation in deep learning. It discusses the challenges of false positives, false negatives, and label errors in datasets, as well as methods for detecting errors and estimating prediction quality. The lecture also explores the use of active learning, meta learning, and automated architecture search in deep learning applications. Various research tracks and further applications are presented, including the importance of mastering perception for automation in safety-critical fields like automated driving and medical imaging.