Prediction rating and performance improvement for segmentation networks by time-dynamic uncertainty estimates / eingereicht von Kira Maag, M. Sc. Wuppertal, 03.08.2021
Inhalt
- Acknowledgments
- Foreword
- Contents
- Introduction
- Review of Basic Material and Related Work
- Neural Networks
- Feed Forward Neural Networks
- Convolutional Neural Networks
- Semantic Segmentation
- Instance Segmentation
- Depth Estimation
- Evaluation Metrics
- Uncertainty Quantification
- Object Tracking
- Classification and Regression Methods for the Prediction of the IoU
- Datasets
- Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
- Related Work
- Method
- Tracking Segments over Time
- Segment-wise Metrics and Time Series
- Prediction of the IoU from Time Series
- Numerical Results
- Discussion
- Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
- False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
- Conclusions & Outlook
- List of Figures
- List of Tables
- List of Algorithms
- List of Notations
- Bibliography