elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Incremental Semi-Supervised Learning from Streams for Object Classification

Chiotellis, Ioannis and Zimmermann, Franziska and Cremers, Daniel and Triebel, Rudolph (2018) Incremental Semi-Supervised Learning from Streams for Object Classification. In: IEEE International Conference on Intelligent Robots and Systems. International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.

[img] PDF
809kB

Abstract

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.

Item URL in elib:https://elib.dlr.de/126183/
Document Type:Conference or Workshop Item (Speech, Poster)
Additional Information:<a href="https://github.com/johny-c/incremental-label-propagation" target="blank">code</a>
Title:Incremental Semi-Supervised Learning from Streams for Object Classification
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Chiotellis, IoannisTUMUNSPECIFIED
Zimmermann, FranziskaUNSPECIFIEDUNSPECIFIED
Cremers, DanielTUMUNSPECIFIED
Triebel, Rudolphrudolph.triebel (at) dlr.dehttps://orcid.org/0000-0002-7975-036X
Date:2018
Journal or Publication Title:IEEE International Conference on Intelligent Robots and Systems
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Status:Published
Keywords:semi-supervised learning, object classification
Event Title:International Conference on Intelligent Robots and Systems (IROS)
Event Location:Madrid, Spain
Event Type:international Conference
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Technik für Raumfahrtsysteme
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Triebel, Rudolph
Deposited On:28 Jan 2019 09:51
Last Modified:31 Jul 2019 20:24

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.