A deep learning method for visual recognition of snake species

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962886" target="_blank" >RIV/49777513:23520/21:43962886 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21230/21:00354247
Result on the web
<a href="http://ceur-ws.org/Vol-2936/paper-128.pdf" target="_blank" >http://ceur-ws.org/Vol-2936/paper-128.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
A deep learning method for visual recognition of snake species
Original language description
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.
Czech name
—
Czech description
—

Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the Working Notes of CLEF 2021 - Conference and Labs of the Evaluation Forum
ISBN
—
ISSN
1613-0073
e-ISSN
—
Number of pages
14
Pages from-to
1512-1525
Publisher name
CEUR-WS
Place of publication
—
Event location
Bucharest, Romania (virtual)
Event date
Sep 21, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)