DeepAI AI Chat
Log In Sign Up

Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning

by   Julian Burghoff, et al.

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.


page 3

page 5

page 7


A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications

A key to ensuring safety in Autonomous Vehicles (AVs) is to avoid any ab...

A Survey on Uncertainty Quantification Methods for Deep Neural Networks: An Uncertainty Source Perspective

Deep neural networks (DNNs) have achieved tremendous success in making a...

Interval Deep Learning for Uncertainty Quantification in Safety Applications

Deep neural networks (DNNs) are becoming more prevalent in important saf...

Fast Uncertainty Estimates in Deep Learning Interatomic Potentials

Deep learning has emerged as a promising paradigm to give access to high...

Uncertainty Quantification of Collaborative Detection for Self-Driving

Sharing information between connected and autonomous vehicles (CAVs) fun...

Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control

A rise in popularity of Deep Neural Networks (DNNs), attributed to more ...

Bayesian Deep Learning Hyperparameter Search for Robust Function Mapping to Polynomials with Noise

Advances in neural architecture search, as well as explainability and in...