Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Lukas Hoyer"'
Publikováno v:
International Journal of Computer Vision
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93bae205df3deb310d448b460c1c2468
http://arxiv.org/abs/2108.12545
http://arxiv.org/abs/2108.12545
Publikováno v:
CVPR
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f552b4b3c6b61a06c9dff9a089525d6
https://doi.org/10.1109/cvpr46437.2021.01098
https://doi.org/10.1109/cvpr46437.2021.01098
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
ICCV 2021
ICCV 2021
omain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks (such as depth estimation) has the potential to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::455f6f95e03f4e2c82557f9fcfaea541
https://hdl.handle.net/20.500.11850/516685
https://hdl.handle.net/20.500.11850/516685
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This process is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ece469e6b608dbf1e2fe39d4b24ac9fa
Publikováno v:
ICCV Workshops
An environment representation (ER) is a substantial part of every autonomous system. It introduces a common interface between perception and other system components, such as decision making, and allows downstream algorithms to deal with abstracted da
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::701ca84bf51d64121b1fe0296e8610da
https://doi.org/10.1109/iccvw.2019.00109
https://doi.org/10.1109/iccvw.2019.00109
Publikováno v:
SSCI
External localization is an essential part for the indoor operation of small or cost-efficient robots, as they are used, for example, in swarm robotics. We introduce a two-stage localization and instance identification framework for arbitrary robots
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8b158dbcfe7c56fbd58791eb55b5740
http://arxiv.org/abs/1810.01665
http://arxiv.org/abs/1810.01665