Overview of FungiCLEF 2022: Fungi Recognition as an Open Set Classification Problem
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Overview of FungiCLEF 2022 : Fungi Recognition as an Open Set Classification Problem. / Picek, Lukáš; Šulc, Milan; Matas, Jiří; Heilmann-Clausen, Jacob.
In: CEUR Workshop Proceedings, Vol. 3180, 2022, p. 1970-1981.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Overview of FungiCLEF 2022
T2 - 2022 Conference and Labs of the Evaluation Forum, CLEF 2022
AU - Picek, Lukáš
AU - Šulc, Milan
AU - Matas, Jiří
AU - Heilmann-Clausen, Jacob
N1 - Publisher Copyright: © 2022 Copyright for this paper by its authors.
PY - 2022
Y1 - 2022
N2 - The main goal of the new LifeCLEF challenge, FungiCLEF 2022: Fungi Recognition as an Open Set Classification Problem, was to provide an evaluation ground for end-to-end fungi species recognition in an open class set scenario. An AI-based fungi species recognition system deployed in the Atlas of Danish Fungi helps mycologists to collect valuable data and allows users to learn about fungi species identification. Advances in fungi recognition from images and metadata will allow continuous improvement of the system deployed in this citizen science project. The training set is based on the Danish Fungi 2020 dataset and contains 295,938 photographs of 1,604 species. For testing, we provided a collection of 59,420 expert-approved observations collected in 2021. The test set includes 1,165 species from the training set and 1,969 unknown species, leading to an open-set recognition problem. This paper provides (i) a description of the challenge task and datasets, (ii) a summary of the evaluation methodology, (iii) a review of the systems submitted by the participating teams, and (iv) a discussion of the challenge results.
AB - The main goal of the new LifeCLEF challenge, FungiCLEF 2022: Fungi Recognition as an Open Set Classification Problem, was to provide an evaluation ground for end-to-end fungi species recognition in an open class set scenario. An AI-based fungi species recognition system deployed in the Atlas of Danish Fungi helps mycologists to collect valuable data and allows users to learn about fungi species identification. Advances in fungi recognition from images and metadata will allow continuous improvement of the system deployed in this citizen science project. The training set is based on the Danish Fungi 2020 dataset and contains 295,938 photographs of 1,604 species. For testing, we provided a collection of 59,420 expert-approved observations collected in 2021. The test set includes 1,165 species from the training set and 1,969 unknown species, leading to an open-set recognition problem. This paper provides (i) a description of the challenge task and datasets, (ii) a summary of the evaluation methodology, (iii) a review of the systems submitted by the participating teams, and (iv) a discussion of the challenge results.
KW - classification
KW - computer vision
KW - fine grained visual categorization
KW - fungi
KW - FungiCLEF
KW - LifeCLEF
KW - machine learning
KW - metadata
KW - open-set recognition
KW - species identification
M3 - Conference article
AN - SCOPUS:85136986038
VL - 3180
SP - 1970
EP - 1981
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
SN - 1613-0073
Y2 - 5 September 2022 through 8 September 2022
ER -
ID: 322653202