Incremental Semi-Supervised Learning from Streams for Object Classification
Chiotellis I, Zimmermann F, Cremers D, Triebel R (2018)
Publication Type: Conference contribution
Publication year: 2018
Journal
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 5743-5749
Conference Proceedings Title: IEEE International Conference on Intelligent Robots and Systems
Event location: Madrid, ESP
ISBN: 9781538680940
DOI: 10.1109/IROS.2018.8593901
Abstract
The Label Propagation (LP) algorithm, first introduced by Zhu and Ghahramani [1], is a semi-supervised method used in transductive learning scenarios, where all data are available already in the beginning. In this work, we present a novel extension of the LP algorithm for applications where data samples are observed sequentially - as is the case in autonomous driving. Specifically, our 'Incremental Label Propagation' algorithm efficiently approximates the so called harmonic solution on a nearest-neighbor graph that is regularly updated by new labeled and unlabeled nodes. We achieve this by reformulating the original algorithm based on an active set of nodes and by introducing a threshold to decide whether the label of a given node should be updated or not. Our method can also deal with graphs that are not fully connected, and we give a formal convergence proof for this general case. In experiments on the challenging KITTI benchmark data stream, we show superior performance in terms of both test accuracy and number of required training labels compared to state-of-the-art online learning methods.
Involved external institutions
Germany (DE)How to cite
APA:
Chiotellis, I., Zimmermann, F., Cremers, D., & Triebel, R. (2018). Incremental Semi-Supervised Learning from Streams for Object Classification. In IEEE International Conference on Intelligent Robots and Systems (pp. 5743-5749). Madrid, ESP: Institute of Electrical and Electronics Engineers Inc..
MLA:
Chiotellis, Ioannis, et al. "Incremental Semi-Supervised Learning from Streams for Object Classification." Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018, Madrid, ESP Institute of Electrical and Electronics Engineers Inc., 2018. 5743-5749.
BibTeX: Download