elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research—Individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes

Bodesheim, Paul und Blunk, Jan und Körschens, Matthias und Brust, Clemens-Alexander und Käding, Christoph und Denzler, Joachim (2022) Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research—Individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes. Mammalian Biology. Springer. doi: 10.1007/s42991-022-00224-8. ISSN 1616-5047.

[img] PDF - Verlagsversion (veröffentlichte Fassung)
2MB

Kurzfassung

Animal re-identification based on image data, either recorded manually by photographers or automatically with camera traps, is an important task for ecological studies about biodiversity and conservation that can be highly automatized with algorithms from computer vision and machine learning. However, fixed identification models only trained with standard datasets before their application will quickly reach their limits, especially for long-term monitoring with changing environmental conditions, varying visual appearances of individuals over time that differ a lot from those in the training data, and new occurring individuals that have not been observed before. Hence, we believe that active learning with human-in-the-loop and continuous lifelong learning is important to tackle these challenges and to obtain high-performance recognition systems when dealing with huge amounts of additional data that become available during the application. Our general approach with image features from deep neural networks and decoupled decision models can be applied to many different mammalian species and is perfectly suited for continuous improvements of the recognition systems via lifelong learning. In our identification experiments, we consider four different taxa, namely two elephant species: African forest elephants and Asian elephants, as well as two species of great apes: gorillas and chimpanzees. Going beyond classical re-identification, our decoupled approach can also be used for predicting attributes of individuals such as gender or age using classification or regression methods. Although applicable for small datasets of individuals as well, we argue that even better recognition performance will be achieved by improving decision models gradually via lifelong learning to exploit huge datasets and continuous recordings from long-term applications. We highlight that algorithms for deploying lifelong learning in real observational studies exist and are ready for use. Hence, lifelong learning might become a valuable concept that supports practitioners when analyzing large-scale image data during long-term monitoring of mammals.

elib-URL des Eintrags:https://elib.dlr.de/186447/
Dokumentart:Zeitschriftenbeitrag
Titel:Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research—Individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Bodesheim, PaulComputer Vision Group, Friedrich-Schiller-Universität Jena, GermanyNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Blunk, JanComputer Vision Group, Friedrich-Schiller-Universität Jena, GermanyNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Körschens, Matthiasmatthias.koerschens (at) uni-jena.dehttps://orcid.org/0000-0002-0755-2006NICHT SPEZIFIZIERT
Brust, Clemens-Alexanderclemens-alexander.brust (at) dlr.dehttps://orcid.org/0000-0001-5419-1998NICHT SPEZIFIZIERT
Käding, ChristophChristoph.Kaeding (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Denzler, JoachimComputer Vision Group, Friedrich-Schiller-Universität Jena, GermanyNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:April 2022
Erschienen in:Mammalian Biology
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
DOI:10.1007/s42991-022-00224-8
Verlag:Springer
ISSN:1616-5047
Status:veröffentlicht
Stichwörter:Active learning, Animal re-identification, Attribute prediction, Continuous learning, Deep learning, Human-in-the-loop, Lifelong learning, Neural networks
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:keine Zuordnung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R - keine Zuordnung
DLR - Teilgebiet (Projekt, Vorhaben):R - keine Zuordnung
Standort: Jena
Institute & Einrichtungen:Institut für Datenwissenschaften > Datenanalyse und -intelligenz
Hinterlegt von: Gerhardus, Andreas
Hinterlegt am:05 Dez 2022 10:51
Letzte Änderung:14 Dez 2022 10:55

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.