Improving Fungi Prototype Representations for Few-Shot Classification
This work addresses accurate fungal identification for mycologists and citizen scientists, supporting biodiversity monitoring, though it appears incremental as it builds on existing prototypical networks.
The paper tackled the challenge of automatic fungal species recognition with highly imbalanced data and few training samples for rare species, achieving over 30 percentage point improvement in Recall@5 compared to the competition baseline.
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.