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

How Robots Learn to Classify New Objects Trained from Small Data Sets

Wang, Tick Son and Marton, Zoltan-Csaba and Brucker, Manuel and Triebel, Rudolph (2017) How Robots Learn to Classify New Objects Trained from Small Data Sets. 1st Conference on Robot Learning, 13-15 Nov 2017, Mountain View, United States.

[img] PDF - Registered users only
843kB

Abstract

In this paper, we address the problem of learning to classify new object classes and instances by adapting a previously trained classifier. The main challenges here are the small amount of newly available training data and the large change in appearance between the new and the old data. To address this we propose a new variant of Progressive Neural Networks (PNN), originally introduced by Rusu et al. [1]. We show that by performing a specific simplification in the adapters, the prediction performance of the resulting PNN can be significantly increased. Furthermore, we give additional insights about when PNNs outperform alternative methods, and provide empirical evaluations on benchmark datasets. Finally, we also suggests a way of using it to augment the functionality of a network by extending it with new classes, addressing the problem of unbalanced classes, i.e. where the new classes are under-represented.

Item URL in elib:https://elib.dlr.de/116840/
Document Type:Conference or Workshop Item (Speech)
Title:How Robots Learn to Classify New Objects Trained from Small Data Sets
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Wang, Tick SonTick.Wang (at) dlr.deUNSPECIFIED
Marton, Zoltan-CsabaZoltan.Marton (at) dlr.dehttps://orcid.org/0000-0002-3035-493X
Brucker, ManuelManuel.Brucker (at) dlr.deUNSPECIFIED
Triebel, RudolphRudolph.Triebel (at) dlr.deUNSPECIFIED
Date:2017
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Progressive Neural Network, Robotic Vision, Transfer Learning
Event Title:1st Conference on Robot Learning
Event Location:Mountain View, United States
Event Type:international Conference
Event Dates:13-15 Nov 2017
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: Brucker, Manuel
Deposited On:08 Dec 2017 16:51
Last Modified:08 Dec 2017 16:51

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.