## Motivation
Automatic recognition of fungi species assists mycologists, citizen scientists and nature enthusiasts in species identification in the wild. Its availability supports the collection of valuable biodiversity data. In practice, species identification typically does not depend solely on the visual observation of the specimen but also on other information available to the observer — such as habitat, substrate, location and time. Thanks to rich metadata, precise annotations, and baselines available to all competitors, the challenge provides a benchmark for image recognition with the use of additional information. Moreover, the toxicity of a mushroom can be crucial for the decision of a mushroom picker. We will explore the decision process within the competition beyond the commonly assumed 0/1 cost function.

## Task Description
Given the set of fungi observations — multiple photographs of the same individual — and corresponding observation metadata, the goal of the task is to return for each image one species based on the likelihood that they might have been observed at that location.

**Note:** *Since the test set contains multiple out-of the-scope classes. Solution have to handle such classes.*

## Context
- This competition is held jointly as part of:
- the LifeCLEF 2022 lab of the CLEF 2022 conference, and of
- the FGVC9 workshop, organized in conjunction with CVPR 2022 conference.

The participants are required to participate to the LifeCLEF lab by registering to it using this [form](https://clef2022-labs-registration.dei.unipd.it/) (and checking "Task 5 - FungiCLEF" of LifeCLEF). Only registered participants can submit a working-note paper to peer-reviewed LifeCLEF proceedings (CEUR-WS) after the competition ends."

*This paper should provide sufficient information to reproduce the final submitted runs.
Only participants who submitted a working-note paper will be part of the officially published ranking used for scientific communication.*

## Best Paper Awards
We will offer a combined credit grant of 5k USD as part of Microsoft's [AI for Earth](https://www.microsoft.com/en-us/ai/ai-for-earth) program to the best papers (up to 3).

In order to claim the Azure price, participants are required to register to LifeCLEF and submit a working-note paper.
The prices will be given to the teams among the highest ranking on the private leaderboard who will have matched these requirements.

See the [Rules](https://www.kaggle.com/c/fungiclef2022/rules) section for more details.

## Organizers

**Machine Learning**
[Lukas Picek](https://www.sites.google.com/view/picekl), Dept. of Cybernetics, FAV, University of West Bohemia, Czechia, lukaspicek@gmail.com
[Milan Sulc](https://sulc.github.io/), Rossum.ai
[Jiri Matas](https://cmp.felk.cvut.cz/~matas/), The Center for Machine Perception Dept. of Cybernetics, FEE, Czech Technical University, Czechia

**Mycology**
[Jacob Heilmann-Clausen](https://globe.ku.dk/staff-list/?pure=en/persons/14882), Center for Macroecology, Evolution and Climate University of Copenhagen, Denmark, jheilmann-clausen@sund.ku.dk