2 citations · 3 across the 4 of their papers we have counts for
4 papers
False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation
Pascal Colling, Matthias Rottmann, Lutz Roese-Koerner +1
We present a novel post-processing tool for semantic segmentation of LiDAR point cloud data, called LidarMetaSeg, which estimates the prediction quality segmentwise. For this purpo…
MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps
Pascal Colling, Lutz Roese-Koerner, Hanno Gottschalk +1
We present a novel region based active learning method for semantic image segmentation, called MetaBox+. For acquisition, we train a meta regression model to estimate the segment-w…
On the Robustness of Active Learning
Lukas Hahn, Lutz Roese-Koerner, Peet Cremer +3
Active Learning is concerned with the question of how to identify the most useful samples for a Machine Learning algorithm to be trained with. When applied correctly, it can be a v…
Fast and Reliable Architecture Selection for Convolutional Neural Networks
Lukas Hahn, Lutz Roese-Koerner, Klaus Friedrichs +1
The performance of a Convolutional Neural Network (CNN) depends on its hyperparameters, like the number of layers, kernel sizes, or the learning rate for example. Especially in sma…