Transformer-based Fine-Grained Fungi Classification in an Open-Set Scenario

Fine-grained fungi classification describes the task of estimating the species of a fungus. The FungiCLEF 2022 challenge started a competition for the best solution to solve this task in an open-set scenario. For our solution, we employ a modern transformer-based classification architecture, use a class-balanced training scheme to handle the class-imbalance and apply heavy data augmentation. We approach the open-set scenario by using the final confidence scores as an indicator for unknown species. With this classification model, we were able to achieve an F1 score of 80.6 and 77.5 on the challenge’s public and private test set, respectively. This resulted in achieving the 7th place in the FungiCLEF 2022 challenge. We provide code at https://github.com/wolfstefan/fungi-classification.