652 citations · 7k across the 163 of their papers we have counts for
4 papers · 2 filters
This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
David Haldimann, Hermann Blum, Roland Siegwart +1
There has been a remarkable progress in the accuracy of semantic segmentation due to the capabilities of deep learning. Unfortunately, these methods are not able to generalize much…
Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes
Nicolas Marchal, Charlotte Moraldo, Roland Siegwart +3
Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed…
Large-scale, real-time visual-inertial localization revisited
Simon Lynen, Bernhard Zeisl, Dror Aiger +5
The overarching goals in image-based localization are scale, robustness and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both do…
The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
Hermann Blum, Paul-Edouard Sarlin, Juan Nieto +2
Deep learning has enabled impressive progress in the accuracy of semantic segmentation. Yet, the ability to estimate uncertainty and detect failure is key for safety-critical appli…