提升罕见真菌识别准确率，用原型网络处理少样本学习问题。
Improving Fungi Prototype Representations for Few-Shot Classification
- 基于原型网络增强类别原型表示，适应少数样本场景。
- 在公开与私有榜单上召回率提升超30个百分点。
- 特别适合稀有物种识别，助力生物多样性监测。
FungiCLEF 2025竞赛聚焦于利用真实野外采集的观测数据实现自动真菌物种识别。准确的识别工具可支持真菌学家与公众科学参与者，大幅提升大规模生物多样性监测能力。该场景下有效的识别系统需应对极度不平衡的类别分布，并在多数物种仅有极少训练样本时仍保持可靠性能，尤其针对那些罕见且记录不足的类群，它们常被标准训练集遗漏。据竞赛组织方统计，约20%的已验证真菌观测（近20,000个实例）属于这些稀有物种。为此，我们提出一种稳健的深度学习方法，基于原型网络增强原型表示，以解决少样本真菌分类问题。该方法在公共（PB）与私有（PR）排行榜上的Recall@5均超过基线30个百分点以上，展现出对常见与稀有真菌物种均具高识别潜力，契合FungiCLEF 2025的核心目标。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。