Rove-Tree-11: The not-so-Wild Rover. A hierarchically structured image dataset for deep metric learning research

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Dokumenter

  • Fulltext

    Accepteret manuskript, 7,02 MB, PDF-dokument

We present a new dataset of images of pinned insects from museum collections along with a ground truth phylogeny (a graph representing the relative evolutionary distance between species). The images include segmentations, and can be used for clustering and deep hierarchical metric learning. As far as we know, this is the first dataset released specifically for generating phylogenetic trees. We provide several benchmarks for deep metric learning using a selection of state-of-the-art methods.
OriginalsprogEngelsk
TitelComputer Vision – ACCV 2022 : 16th Asian Conference on Computer Vision, Macao, China, December 4–8, 2022, Proceedings, Part I
ForlagSpringer
Publikationsdato2023
Sider2967-2983
StatusUdgivet - 2023
Begivenhed16th Asian Conference on Computer Vision, ACCV 2022 - Macao, Kina
Varighed: 4 dec. 20228 dec. 2022

Konference

Konference16th Asian Conference on Computer Vision, ACCV 2022
LandKina
ByMacao
Periode04/12/202208/12/2022
NavnLecture Notes in Computer Science
Vol/bind13841
ISSN0302-9743

ID: 324372038