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

Interactive Visualization based Active Learning

Babaee, Mohammadreza and Tsoukalas, Stefanos and Rigoll, Gerhard and Datcu, Mihai (2014) Interactive Visualization based Active Learning. European Conference on Computer Vision (ECCV) 2014, 06-12 Sep 2014, Zurich, Switzerland.

Full text not available from this repository.

Official URL: http://vision.cs.utexas.edu/hmcv2014/babaee_etal_hmcv2014.pdf


Active learning aims to label the most informative data points in order to minimize the cost of labeling [1]. In this work, we introduce a human based approach, namely First Certain Wrong Labeled (FCWL) to select points for labeling. It is based on a ranked list of predictions ordered by confidence, from which the user selects the highest ranking incorrect prediction. The experimental results show the improvement in performance of this method compared to others.

Item URL in elib:https://elib.dlr.de/100308/
Document Type:Conference or Workshop Item (Speech)
Additional Information:ECCV 2014 Workshop: Human-Machine Communication for Visual Recognition and Search (HMCV)
Title:Interactive Visualization based Active Learning
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Babaee, MohammadrezaTechnical University Munich, GermanyUNSPECIFIED
Tsoukalas, StefanosTechnical University Munich, GermanyUNSPECIFIED
Rigoll, GerhardTechnical University Munich, GermanyUNSPECIFIED
Datcu, Mihaimihai.datcu (at) dlr.deUNSPECIFIED
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 1-4
Keywords:Active Learning, visualization
Event Title:European Conference on Computer Vision (ECCV) 2014
Event Location:Zurich, Switzerland
Event Type:international Conference
Event Dates:06-12 Sep 2014
Organizer:ETH Zurich
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Schwarz, Gottfried
Deposited On:03 Dec 2015 10:27
Last Modified:10 May 2016 23:37

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.