Narr A, Triebel R, Cremers D (2016)
Publication Type: Conference contribution
Publication year: 2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 2016-June
Pages Range: 227-233
Conference Proceedings Title: Proceedings - IEEE International Conference on Robotics and Automation
Event location: Stockholm, SWE
ISBN: 9781467380263
DOI: 10.1109/ICRA.2016.7487138
We present a new Active Learning approach for classifying objects from streams of 3D point cloud data. The major problems here are the non-uniform occurrence of class instances and the unbalanced numbers of samples per class. We show that standard online learning methods based on decision trees perform comparably bad for such data streams, which are however particularly relevant for mobile robots that need to learn semantics persistently. To address this, we use Mondrian forests (MF), a recent online learning algorithm that is independent on the data order. We present an extension of that algorithm and show that MF are less overconfident than standard Random Forests. In experiments on the KITTI benchmark, we show that this leads to a substantially improved classification performance for data streams, rendering our approach very attractive for lifelong robot learning applications.
APA:
Narr, A., Triebel, R., & Cremers, D. (2016). Stream-based Active Learning for efficient and adaptive classification of 3D objects. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 227-233). Stockholm, SWE: Institute of Electrical and Electronics Engineers Inc..
MLA:
Narr, Alexander, Rudolph Triebel, and Daniel Cremers. "Stream-based Active Learning for efficient and adaptive classification of 3D objects." Proceedings of the 2016 IEEE International Conference on Robotics and Automation, ICRA 2016, Stockholm, SWE Institute of Electrical and Electronics Engineers Inc., 2016. 227-233.
BibTeX: Download