150 citations · 365 across the 15 of their papers we have counts for
5 papers · 1 filter
Continual Adaptation of Semantic Segmentation using Complementary 2D-3D Data Representations
Jonas Frey, Hermann Blum, Francesco Milano +2
Semantic segmentation networks are usually pre-trained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the traini…
See Yourself in Others: Attending Multiple Tasks for Own Failure Detection
Boyang Sun, Jiaxu Xing, Hermann Blum +2
Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth esti…
Self-Improving Semantic Perception for Indoor Localisation
Hermann Blum, Francesco Milano, René Zurbrügg +3
We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fi…
SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
Robin Chan, Krzysztof Lis, Svenja Uhlemeyer +6
State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle pre…
Pixel-wise Anomaly Detection in Complex Driving Scenes
Giancarlo Di Biase, Hermann Blum, Roland Siegwart +1
The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as au…