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

Selecting CNN Features for Online Learning of 3D Objects

Ullrich, Monika and Ali, Haider and Durner, Maximilian and Marton, Zoltan-Csaba and Triebel, Rudolph (2017) Selecting CNN Features for Online Learning of 3D Objects. In: IEEE International Conference on Intelligent Robots and Systems. IEEE. IROS 2017, 24-28 Sept 2017, Vancouver, Canada.

[img] PDF - Only accessible within DLR


We present a novel method for classifying 3D objects that is particularly tailored for the requirements in robotic applications. The major challenges here are the comparably small amount of available training data and the fact that often data is perceived in streams and not in fixed-size pools. Traditional state-of-the-art learning methods, however, require a large amount of training data, and their online learning capabilities are usually limited. Therefore, we propose a modality-specific selection of convolutional neural networks (CNN), pre-trained or fine-tuned, in combination with a classifier that is designed particularly for online learning from data streams, namely the Mondrian Forest (MF). We show that this combination of trained features obtained from a CNN can be improved further if a feature selection algorithm is applied. In our experiments, we use the resulting features both with a MF and a linear Support Vector Machine (SVM). With SVM we beat the state of the art on an RGB-D dataset, while with MF a strong result for active learning is achieved.

Item URL in elib:https://elib.dlr.de/116731/
Document Type:Conference or Workshop Item (Speech)
Title:Selecting CNN Features for Online Learning of 3D Objects
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Ullrich, MonikaMonika.Ullrich (at) dlr.deUNSPECIFIED
Ali, HaiderHaider.Ali (at) dlr.deUNSPECIFIED
Durner, MaximilianMaximilian.Durner (at) dlr.dehttps://orcid.org/0000-0001-8885-5334
Marton, Zoltan-CsabaZoltan.Marton (at) dlr.dehttps://orcid.org/0000-0002-3035-493X
Triebel, Rudolphrudolph.triebel (at) dlr.deUNSPECIFIED
Journal or Publication Title:IEEE International Conference on Intelligent Robots and Systems
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Keywords:feature selection, deep learned features, online learning
Event Title:IROS 2017
Event Location:Vancouver, Canada
Event Type:international Conference
Event Dates:24-28 Sept 2017
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Durner, Maximilian
Deposited On:19 Dec 2017 11:07
Last Modified:20 Jun 2021 15:50

Repository Staff Only: item control page

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