Optimizing Fine-Grained Fungi Classification for Diverse Application-Oriented Open-Set Metrics

Fine-grained fungi species classification is an important task to support distinguishing edible and poisonous fungi and thus, reducing the risk of accidental poisoning. Therefore, the FungiCLEF 2023 challenge seeks to find the best solution for this task considering multiple metrics with each having a different application in focus like e.g., a low confusion of edible and poisonous fungi. We propose a method to approach the different metrics by exploiting modern deep learning networks, strong data augmentation and class-balanced training. The challenge assumes an open-set scenario which includes unknown classes during evaluation which we identify by a confidence thresholding approach. With our method, we achieved the 2nd place in the challenge with good scores across all metrics. Code is available at: https://github.com/wolfstefan/fungi2023.