FungiTastic: A multi-modal dataset and benchmark for image categorization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00384625" target="_blank" >RIV/68407700:21230/25:00384625 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/49777513:23520/25:43976618

Výsledek na webu

<a href="https://doi.org/10.1109/CVPRW67362.2025.00192" target="_blank" >https://doi.org/10.1109/CVPRW67362.2025.00192</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPRW67362.2025.00192" target="_blank" >10.1109/CVPRW67362.2025.00192</a>

Jazyk výsledku

angličtina

Název v původním jazyce

FungiTastic: A multi-modal dataset and benchmark for image categorization

Popis výsledku v původním jazyce

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 on HuggingFace, and a framework for model training. The documentation and the baselines are available at GitHub and Kaggle.

Název v anglickém jazyce

FungiTastic: A multi-modal dataset and benchmark for image categorization

Popis výsledku anglicky

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 on HuggingFace, and a framework for model training. The documentation and the baselines are available at GitHub and Kaggle.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/SS73020004" target="_blank" >SS73020004: FunDive: Mapování a monitoring diverzity hub se zaměřením na druhovou ochranu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

ISBN

979-8-3315-9994-2

ISSN

2160-7508

e-ISSN

2160-7516

Počet stran výsledku

11

Strana od-do

2037-2047

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Nashville

Datum konání akce

11. 6. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—