Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Chamidullin, Rail | |
dc.contributor.author | Šulc, Milan | |
dc.contributor.author | Matas, Jiří | |
dc.contributor.author | Picek, Lukáš | |
dc.date.accessioned | 2022-03-28T10:00:30Z | - |
dc.date.available | 2022-03-28T10:00:30Z | - |
dc.date.issued | 2021 | |
dc.identifier.citation | CHAMIDULLIN, R. ŠULC, M. MATAS, J. PICEK, L. A deep learning method for visual recognition of snake species. In Proceedings of the Working Notes of CLEF 2021 - Conference and Labs of the Evaluation Forum. neuvedeno: CEUR-WS, 2021. s. 1512-1525. ISBN: neuvedeno , ISSN: 1613-0073 | cs |
dc.identifier.isbn | neuvedeno | |
dc.identifier.issn | 1613-0073 | |
dc.identifier.uri | 2-s2.0-85113481716 | |
dc.identifier.uri | http://hdl.handle.net/11025/47277 | |
dc.format | 14 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | CEUR-WS | en |
dc.relation.ispartofseries | Proceedings of the Working Notes of CLEF 2021 - Conference and Labs of the Evaluation Forum | en |
dc.rights | © authors | en |
dc.title | A deep learning method for visual recognition of snake species | en |
dc.type | konferenční příspěvek | cs |
dc.type | ConferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | The paper presents a method for image-based snake species identification. The proposed method is based on deep residual neural networks - ResNeSt, ResNeXt and ResNet - fine-tuned from ImageNet pre-trained checkpoints. We achieve performance improvements by: discarding predictions of species that do not occur in the country of the query; combining predictions from an ensemble of classifiers; and applying mixed precision training, which allows training neural networks with larger batch size. We experimented with loss functions inspired by the considered metrics: soft F1 loss and weighted cross entropy loss. However, the standard cross entropy loss achieved superior results both in accuracy and in F1 measures. The proposed method scored third in the SnakeCLEF 2021 challenge, achieving 91.6% classification accuracy, Country F1 Score of 0.860, and F1 Score of 0.830. | en |
dc.subject.translated | Snake species identification | en |
dc.subject.translated | Fine-grained classification | en |
dc.subject.translated | Computer vision | en |
dc.subject.translated | Convolutional neural networks | en |
dc.subject.translated | Deep learning | en |
dc.type.status | Peer-reviewed | en |
dc.identifier.obd | 43933885 | |
dc.project.ID | SGS-2019-027/Inteligentní metody strojového vnímání a porozumění 4 | cs |
Vyskytuje se v kolekcích: | Konferenční příspěvky / Conference Papers (KKY) OBD |
Soubory připojené k záznamu:
Soubor | Velikost | Formát | |
---|---|---|---|
Chamidullin_A_deep_learning_paper-128_2021.pdf | 918,87 kB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/47277
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.