36 citations · 48 across the 6 of their papers we have counts for
7 papers
Revisiting Gradient-based Uncertainty for Monocular Depth Estimation
Julia Hornauer, Amir El-Ghoussani, Vasileios Belagiannis
Monocular depth estimation, similar to other image-based tasks, is prone to erroneous predictions due to ambiguities in the image, for example, caused by dynamic objects or shadows…
Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation
Amir El-Ghoussani, Julia Hornauer, Gustavo Carneiro +1
In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets. However, this comes…
Out-of-Distribution Detection for Monocular Depth Estimation
Julia Hornauer, Adrian Holzbock, Vasileios Belagiannis
In monocular depth estimation, uncertainty estimation approaches mainly target the data uncertainty introduced by image noise. In contrast to prior work, we address the uncertainty…
Heatmap-based Out-of-Distribution Detection
Julia Hornauer, Vasileios Belagiannis
Our work investigates out-of-distribution (OOD) detection as a neural network output explanation problem. We learn a heatmap representation for detecting OOD images while visualizi…
Gradient-based Uncertainty for Monocular Depth Estimation
Julia Hornauer, Vasileios Belagiannis
In monocular depth estimation, disturbances in the image context, like moving objects or reflecting materials, can easily lead to erroneous predictions. For that reason, uncertaint…
Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
Julia Hornauer, Lazaros Nalpantidis, Vasileios Belagiannis
Real-world perception systems in many cases build on hardware with limited resources to adhere to cost and power limitations of their carrying system. Deploying deep neural network…
Few-Shot Microscopy Image Cell Segmentation
Youssef Dawoud, Julia Hornauer, Gustavo Carneiro +1
Automatic cell segmentation in microscopy images works well with the support of deep neural networks trained with full supervision. Collecting and annotating images, though, is not…