Selecting CNN features for online learning of 3D objects

Monika Ullrich, Haider Ali, Maximilian Durner, Zoltan Csaba Marton, Rudolph Triebel

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

6 Zitate (Scopus)

Abstract

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.

OriginalspracheEnglisch
TitelIROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten5086-5091
Seitenumfang6
ISBN (elektronisch)9781538626825
DOIs
PublikationsstatusVeröffentlicht - 13 Dez. 2017
Veranstaltung2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017 - Vancouver, Kanada
Dauer: 24 Sept. 201728 Sept. 2017

Publikationsreihe

NameIEEE International Conference on Intelligent Robots and Systems
Band2017-September
ISSN (Print)2153-0858
ISSN (elektronisch)2153-0866

Konferenz

Konferenz2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017
Land/GebietKanada
OrtVancouver
Zeitraum24/09/1728/09/17

Fingerprint

Untersuchen Sie die Forschungsthemen von „Selecting CNN features for online learning of 3D objects“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren