Do Not Lose to Losses for SnakeCLEF2024

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43973203" target="_blank" >RIV/49777513:23520/24:43973203 - isvavai.cz</a>
Result on the web
<a href="https://ceur-ws.org/Vol-3740/paper-207.pdf" target="_blank" >https://ceur-ws.org/Vol-3740/paper-207.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Do Not Lose to Losses for SnakeCLEF2024
Original language description
This paper presents participation in the SnakeCLEF 2024 challenge, which aims to automate the identification of snake species. We explore various custom loss functions that incorporate the venomousness of snakes. These loss functions are used to train the Swin-v2 tiny model with same training specification as baseline solution to accurately measure the impact of custom loss functions. Swin-v2 tiny model is beneficial due to its low computational demand and opens the possibility for use in handheld devices. Our results show that the best approach for maximising performance on the custom competition metrics is to apply a soft target set according to the venomousness of the snake. The best accuracy is achieved by the model trained with loss, which weights the different classes according to the number of their instances.
Czech name
—
Czech description
—

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)