Logo des Repositoriums
 
Textdokument

Exploiting Web Images for Moth Species Classification

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Zusatzinformation

Datum

2021

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik, Bonn

Zusammenfassung

Due to shrinking habitats, moth populations are declining rapidly. An automated moth population monitoring tool is needed to support conservationists in making informed decisions for counteracting this trend. A non-invasive tool would involve the automatic classification of images of moths, a fine-grained recognition problem. Currently, the lack of images annotated by experts is the main hindrance to such a classification model. To understand how to achieve acceptable predictive accuracies, we investigate the effect of differently sized datasets and data acquired from the Internet. We find the use of web data immensely beneficial and observe that few images from the evaluation domain are enough to mitigate the domain shift in web data. Our experiments show that counteracting the domain shift may yield a relative reduction of the error rate of over 60%. Lastly, the effect of label noise in web data and proposed filtering techniques are analyzed and evaluated.

Beschreibung

Böhlke,Julia; Korsch, Dimitri; Bodesheim, Paul; Denzler, Joachim (2021): Exploiting Web Images for Moth Species Classification. INFORMATIK 2021. DOI: 10.18420/informatik2021-038. Gesellschaft für Informatik, Bonn. PISSN: 1617-5468. ISBN: 978-3-88579-708-1. pp. 481-498. Workshop: Computer Science for Biodiversity (CS4BIODiversity). Berlin. 27. September - 1. Oktober 2021

Zitierform

Tags