Awet Haileslassie Gebrehiwot

Awet Haileslassie Gebrehiwot

Auto-generated profile, based on publicly available information

Awet Haileslassie Gebrehiwot

Dept of Cybernetics Czech Technical University in Prague FEE

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
AGAwet Haileslassie Gebrehiwot
Awet Haileslassie Gebrehiwot
PVPatrik Vacek
Patrik Vacek
DHDavid Hurych
David Hurych
KZKarel Zimmermann
Karel Zimmermann
PPPatrick Perez
Patrick Perez
TSTomas Svoboda
Tomas Svoboda
Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is especially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are large, and manual labeling is very challenging. We propose to leverage sequences of point clouds to boost the pseudo-labeling technique in a teacher-student setup via training multiple teachers, each with access to different temporal information. This set of teachers, dubbed Concordance , provides higher quality pseudo-labels for student training than standard methods. The output of multiple teachers is combined via a novel pseudo-label confidence-guided criterion. Our experimental evaluation focuses on the 3D point cloud domain and urban driving scenarios. We show the performance of our method applied to 3D semantic segmentation and 3D object detection on three benchmark datasets. Our approach, which uses only 20% manual labels, outperforms some fully supervised methods. A notable performance boost is achieved for classes rarely appearing in training data. Our codes will be made publicly available.

5 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
AGAwet Haileslassie Gebrehiwot
Awet Haileslassie Gebrehiwot
PVPatrik Vacek
Patrik Vacek
DHDavid Hurych
David Hurych
KZKarel Zimmermann
Karel Zimmermann
PPPatrick Perez
Patrick Perez
TSTomáš Svoboda
Tomáš Svoboda
Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are large, and manual labeling is very challenging. We propose to leverage sequences of point clouds to boost the pseudolabeling technique in a teacher-student setup via training multiple teachers, each with access to different temporal information. This set of teachers, dubbed Concordance, provides higher quality pseudo-labels for student training than standard methods. The output of multiple teachers is combined via a novel pseudo label confidence-guided criterion. Our experimental evaluation focuses on the 3D point cloud domain and urban driving scenarios. We show the performance of our method applied to 3D semantic segmentation and 3D object detection on three benchmark datasets. Our approach, which uses only 20% manual labels, outperforms some fully supervised methods. A notable performance boost is achieved for classes rarely appearing in training data.