Chiotellis, Ioannis und Zimmermann, Franziska und Cremers, Daniel und Triebel, Rudolph (2018) Incremental Semi-Supervised Learning from Streams for Object Classification. In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018. International Conference on Intelligent Robots and Systems (IROS), 2018-10-01 - 2018-10-05, Madrid, Spain. doi: 10.1109/IROS.2018.8593901. ISBN 978-153868094-0. ISSN 2153-0858.
![]() |
PDF
809kB |
Kurzfassung
The Label Propagation (LP) algorithm, first introduced by Zhu and Ghahramani, 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.
elib-URL des Eintrags: | https://elib.dlr.de/126183/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag, Poster) | ||||||||||||||||||||
Zusätzliche Informationen: | <a href="https://github.com/johny-c/incremental-label-propagation" target="blank">code</a> | ||||||||||||||||||||
Titel: | Incremental Semi-Supervised Learning from Streams for Object Classification | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | 2018 | ||||||||||||||||||||
Erschienen in: | 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018 | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Ja | ||||||||||||||||||||
DOI: | 10.1109/IROS.2018.8593901 | ||||||||||||||||||||
ISSN: | 2153-0858 | ||||||||||||||||||||
ISBN: | 978-153868094-0 | ||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||
Stichwörter: | semi-supervised learning, object classification | ||||||||||||||||||||
Veranstaltungstitel: | International Conference on Intelligent Robots and Systems (IROS) | ||||||||||||||||||||
Veranstaltungsort: | Madrid, Spain | ||||||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||||||
Veranstaltungsbeginn: | 1 Oktober 2018 | ||||||||||||||||||||
Veranstaltungsende: | 5 Oktober 2018 | ||||||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||||||||||
HGF - Programmthema: | Technik für Raumfahrtsysteme | ||||||||||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||||||
DLR - Forschungsgebiet: | R SY - Technik für Raumfahrtsysteme | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Vorhaben Multisensorielle Weltmodellierung (alt) | ||||||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) > Perzeption und Kognition | ||||||||||||||||||||
Hinterlegt von: | Triebel, Rudolph | ||||||||||||||||||||
Hinterlegt am: | 28 Jan 2019 09:51 | ||||||||||||||||||||
Letzte Änderung: | 09 Jul 2024 14:53 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags