Full metadata record
DC FieldValueLanguage
dc.contributor.authorPicek, Lukáš
dc.contributor.authorŠulc, Milan
dc.contributor.authorMatas, Jiří
dc.contributor.authorJeppesen, Thomas S.
dc.contributor.authorHeilmann-Clausen, Jacob
dc.contributor.authorLassoe, Thomas
dc.contributor.authorFroslev, Tobias
dc.date.accessioned2023-02-13T11:00:19Z-
dc.date.available2023-02-13T11:00:19Z-
dc.date.issued2022
dc.identifier.citationPICEK, L. ŠULC, M. MATAS, J. JEPPESEN, TS. HEILMANN-CLAUSEN, J. LASSOE, T. FROSLEV, T. Danish Fungi 2020 - Not Just Another Image Recognition Dataset. In Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022. New York: IEEE, 2022. s. 3281-3291. ISBN: 978-1-66540-915-5 , ISSN: 2472-6737cs
dc.identifier.isbn978-1-66540-915-5
dc.identifier.issn2472-6737
dc.identifier.uri2-s2.0-85122859027
dc.identifier.urihttp://hdl.handle.net/11025/51450
dc.format11 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseriesProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022en
dc.rights© IEEEen
dc.titleDanish Fungi 2020 - Not Just Another Image Recognition Dataseten
dc.typekonferenční příspěvekcs
dc.typeConferenceObjecten
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedWe introduce a novel fine-grained dataset and bench-mark, the Danish Fungi 2020 (DF20). The dataset, constructed from observations submitted to the Atlas of Danish Fungi, is unique in its taxonomy-accurate class labels, small number of errors, highly unbalanced long-tailed class distribution, rich observation metadata, and well-defined class hierarchy. DF20 has zero overlap with ImageNet, al-lowing unbiased comparison of models fine-tuned from publicly available ImageNet checkpoints. The proposed evaluation protocol enables testing the ability to improve classification using metadata - e.g. precise geographic location, habitat, and substrate, facilitates classifier calibration testing, and finally allows to study the impact of the device settings on the classification performance. Experiments using Convolutional Neural Networks (CNN) and the recent Vision Transformers (ViT) show that DF20 presents a challenging task. Interestingly, ViT achieves results su-perior to CNN baselines with 80.45% accuracy and 0.743 macro F1 score, reducing the CNN error by 9% and 12% respectively. A simple procedure for including metadata into the decision process improves the classification accuracy by more than 2.95 percentage points, reducing the error rate by 15%. The source code for all methods and experiments is available at https://sites.google.com/view/danish-fungi-dataset.en
dc.subject.translatedComputer visionen
dc.subject.translatedConvolutionen
dc.subject.translatedConvolutional neural networksen
dc.subject.translatedErrorsen
dc.subject.translatedImage recognitionen
dc.subject.translatedMetadataen
dc.subject.translatedObject detectionen
dc.identifier.doi10.1109/WACV51458.2022.00334
dc.type.statusPeer-revieweden
dc.identifier.document-number800471203036
dc.identifier.obd43937004
dc.project.IDLO1506/PUNTIS - Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnostcs
dc.project.IDSGS-2019-027/Inteligentní metody strojového vnímání a porozumění 4cs
Appears in Collections:Konferenční příspěvky / Conference papers (NTIS)
Konferenční příspěvky / Conference Papers (KKY)
OBD

Files in This Item:
File SizeFormat 
Picek_Danish_Fungi_2020_-_Not_Just_Another_Image_Recognition_Dataset_WACV_2022_paper.pdf10,01 MBAdobe PDFView/Open
Show simple item record


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/51450

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

search
navigation
  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. OBD