Using Diverse Neural Networks for Safer Human Pose Estimation: Towards Making Neural Networks Know When They Don’t Know
Patrick Schlosser,Christoph Ledermann,Patrick Schlosser,Christoph Ledermann
In recent years, human pose estimation has seen great improvements by the use of neural networks. However, these approaches are unsuitable for safety-critical applications such as human-robot interaction (HRI), as no guarantees are given whether a produced detection is correct or not and false detections with high confidence scores are produced on a regular basis. In this work, we propose a method...
