Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
This work tackles the problem of making deep learning reliable in safety-critical domains, but it is incremental as it surveys existing methods without introducing new paradigms.
The paper addresses the challenge of uncertainty quantification in deep neural networks for safety-critical applications like automated driving and medical imaging, presenting methods to teach DNNs to be uncertain with new object classes and to learn from few labels, but notes these approaches incur massive computational overheads of an order of magnitude or more compared to standard training.
Bringing deep neural networks (DNNs) into safety critical applications such as automated driving, medical imaging and finance, requires a thorough treatment of the model's uncertainties. Training deep neural networks is already resource demanding and so is also their uncertainty quantification. In this overview article, we survey methods that we developed to teach DNNs to be uncertain when they encounter new object classes. Additionally, we present training methods to learn from only a few labels with help of uncertainty quantification. Note that this is typically paid with a massive overhead in computation of an order of magnitude and more compared to ordinary network training. Finally, we survey our work on neural architecture search which is also an order of magnitude more resource demanding then ordinary network training.