2 papers
cs.LG2020
Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning
Christian Haase-Schütz, Rainer Stal, Heinz Hertlein +1
State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typica…
cs.RO2019
Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
Di Feng, Christian Haase-Schütz, Lars Rosenbaum +5
Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually e…