We introduce a new, challenging benchmark and a dataset, FungiTastic, based on fungal records continuously collected over a twenty-year span. The dataset is labelled and curated by experts and consists of about 350k multimodal observations of 6k fine-grained categories (species). The fungi observations include photographs and additional data, e.g., meteorological and climatic data, satellite images, and body part segmentation masks. FungiTastic is one of the few benchmarks that include a test set with DNA-sequenced ground truth of unprecedented label reliability. The benchmark is designed to support (i) standard closed-set classification, (ii) open-set classification, (iii) multi-modal classification, (iv) few-shot learning, (v) domain shift, and many more. We provide tailored baselines for many use cases, a multitude of ready-to-use pre-trained models onthis https URL, and a framework for model training. The documentation and the baselines are available atthis https URLandthis https URL.
View on arXiv@article{picek2025_2408.13632,
title={ FungiTastic: A multi-modal dataset and benchmark for image categorization },
author={ Lukas Picek and Klara Janouskova and Vojtech Cermak and Jiri Matas },
journal={arXiv preprint arXiv:2408.13632},
year={ 2025 }
}