Title:	Danish Fungi 2020 - Not Just Another Image Recognition Dataset
Authors:	Picek, Lukáš Šulc, Milan Matas, Jiří Jeppesen, Thomas S. Heilmann-Clausen, Jacob Lassoe, Thomas Froslev, Tobias
Citation:	PICEK, 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: 2472-6737
Issue Date:	2022
Publisher:	IEEE
Document type:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85122859027 http://hdl.handle.net/11025/51450
ISBN:	978-1-66540-915-5
ISSN:	2472-6737
Keywords in different language:	Computer vision;Convolution;Convolutional neural networks;Errors;Image recognition;Metadata;Object detection
Abstract in different language:	We 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.
Rights:	© IEEE
Appears in Collections:	Konferenční příspěvky / Conference papers (NTIS) Konferenční příspěvky / Conference Papers (KKY) OBD

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