no code implementations • 29 Dec 2022 • Krzysztof Lis, Matthias Rottmann, Sina Honari, Pascal Fua, Mathieu Salzmann
In other words, vision transformers trained to segment a fixed set of object classes generalize to objects well beyond this set.
1 code implementation • 4 Oct 2022 • Krzysztof Lis, Sina Honari, Pascal Fua, Mathieu Salzmann
While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases.
2 code implementations • 30 Apr 2021 • Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Pascal Fua, Mathieu Salzmann, Matthias Rottmann
State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes.
no code implementations • 25 Dec 2020 • Krzysztof Lis, Sina Honari, Pascal Fua, Mathieu Salzmann
Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector.
3 code implementations • ICCV 2019 • Krzysztof Lis, Krishna Nakka, Pascal Fua, Mathieu Salzmann
In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time.
no code implementations • 23 Mar 2018 • Weizhe Liu, Krzysztof Lis, Mathieu Salzmann, Pascal Fua
In this paper, we explicitly model the scale changes and reason in terms of people per square-meter.