Improving Fungi Prototype Representations for Few-Shot Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Traore, Abdarahmane, Hervet, Éric, Couturier, Andy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914036252147712
author Traore, Abdarahmane
Hervet, Éric
Couturier, Andy
author_facet Traore, Abdarahmane
Hervet, Éric
Couturier, Andy
contents The FungiCLEF 2025 competition addresses the challenge of automatic fungal species recognition using realistic, field-collected observational data. Accurate identification tools support both mycologists and citizen scientists, greatly enhancing large-scale biodiversity monitoring. Effective recognition systems in this context must handle highly imbalanced class distributions and provide reliable performance even when very few training samples are available for many species, especially rare and under-documented taxa that are often missing from standard training sets. According to competition organizers, about 20\% of all verified fungi observations, representing nearly 20,000 instances, are associated with these rarely recorded species. To tackle this challenge, we propose a robust deep learning method based on prototypical networks, which enhances prototype representations for few-shot fungal classification. Our prototypical network approach exceeds the competition baseline by more than 30 percentage points in Recall@5 on both the public (PB) and private (PR) leaderboards. This demonstrates strong potential for accurately identifying both common and rare fungal species, supporting the main objectives of FungiCLEF 2025.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11020
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Fungi Prototype Representations for Few-Shot Classification
Traore, Abdarahmane
Hervet, Éric
Couturier, Andy
Computer Vision and Pattern Recognition
The FungiCLEF 2025 competition addresses the challenge of automatic fungal species recognition using realistic, field-collected observational data. Accurate identification tools support both mycologists and citizen scientists, greatly enhancing large-scale biodiversity monitoring. Effective recognition systems in this context must handle highly imbalanced class distributions and provide reliable performance even when very few training samples are available for many species, especially rare and under-documented taxa that are often missing from standard training sets. According to competition organizers, about 20\% of all verified fungi observations, representing nearly 20,000 instances, are associated with these rarely recorded species. To tackle this challenge, we propose a robust deep learning method based on prototypical networks, which enhances prototype representations for few-shot fungal classification. Our prototypical network approach exceeds the competition baseline by more than 30 percentage points in Recall@5 on both the public (PB) and private (PR) leaderboards. This demonstrates strong potential for accurately identifying both common and rare fungal species, supporting the main objectives of FungiCLEF 2025.
title Improving Fungi Prototype Representations for Few-Shot Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.11020