1 code implementation • CVPR 2023 • Tobias Kalb, Jürgen Beyerer
Deep neural networks for scene perception in automated vehicles achieve excellent results for the domains they were trained on.
no code implementations • 21 Feb 2023 • Tobias Kalb, Niket Ahuja, Jingxing Zhou, Jürgen Beyerer
Specifically, we compare the well-researched CNNs to recently proposed Transformers and Hybrid architectures, as well as the impact of the choice of novel normalization layers and different decoder heads.
1 code implementation • 20 Sep 2022 • Tobias Kalb, Björn Mauthe, Jürgen Beyerer
Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains.
no code implementations • 16 Sep 2022 • Tobias Kalb, Masoud Roschani, Miriam Ruf, Jürgen Beyerer
Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation.
Class-Incremental Semantic Segmentation Continual Semantic Segmentation +6
1 code implementation • 16 Sep 2022 • Tobias Kalb, Jürgen Beyerer
Therefore, in a set of experiments and representational analyses, we demonstrate that the semantic shift of the background class and a bias towards new classes are the major causes of forgetting in CiSS.
Class-Incremental Semantic Segmentation Incremental Learning +2
1 code implementation • 16 Jul 2019 • Thomas Golda, Tobias Kalb, Arne Schumann, Jürgen Beyerer
In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications.
Ranked #14 on Multi-Person Pose Estimation on CrowdPose