Search Results for author: Jakob Gawlikowski

Found 4 papers, 1 papers with code

The Unreasonable Effectiveness of Deep Evidential Regression

2 code implementations20 May 2022 Nis Meinert, Jakob Gawlikowski, Alexander Lavin

There is a significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains.

regression Uncertainty Quantification

A Survey of Uncertainty in Deep Neural Networks

no code implementations7 Jul 2021 Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, JongSeok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang, Richard Bamler, Xiao Xiang Zhu

Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications.

Data Augmentation

Leveraging Graph and Deep Learning Uncertainties to Detect Anomalous Trajectories

no code implementations4 Jul 2021 Sandeep Kumar Singh, Jaya Shradha Fowdur, Jakob Gawlikowski, Daniel Medina

Our experimental results suggest that the graphical representation of traffic patterns improves the ability of the DL models, such as evidential and Monte Carlo dropout, to learn the temporal-spatial correlation of data and associated uncertainties.

Out-of-distribution detection in satellite image classification

no code implementations9 Apr 2021 Jakob Gawlikowski, Sudipan Saha, Anna Kruspe, Xiao Xiang Zhu

In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area.

Classification General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.