解决植物分类中细粒度识别与长尾分布共存的难题
Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy
- 设计双边界损失函数，优化类别间决策边界
- 在多个真实数据集上显著提升稀有类别的识别准确率
- 适合生态监测与开放世界植物识别场景
生态学中的科、属、种分类对生物多样性监测和保护至关重要。现有计算机视觉方法通常孤立处理细粒度识别与长尾学习问题。然而，在真实部署中，时空域偏移、层级分类结构以及未见类别的问题常同时出现，导致模型在开放世界下表现脆弱。本文提出 TaxoNet，一种具有理论支撑的双边界嵌入学习框架，通过重塑类别不平衡下的决策边界，在增强稀有类别表征几何结构的同时提升细粒度区分能力。我们在包含 Google Auto-Arborist（城市树木图像）、iNaturalist（跨异质生态系统的植物观测）和 NAFlora-Mini（标本馆采集）在内的多种植物数据集上评估了 TaxoNet 在包含多重挑战的开放世界设置下的性能。结果表明，TaxoNet 持续优于强基线模型，包括多模态基础模型。
原文摘要 · Abstract (English)
Taxonomic classification of ecological families, genera, and species underpins biodiversity monitoring and conservation. Existing computer vision methods typically address fine-grained recognition and long-tailed learning in isolation. However, additional challenges such as spatiotemporal domain shift, hierarchical taxonomic structure, and previously unseen taxa often co-occur in real-world deployment, leading to brittle performance under open-world conditions. We propose TaxoNet, an embedding learning framework with a theoretically grounded dual-margin objective that reshapes class decision boundaries under class imbalance to improve fine-grained discrimination while strengthening rare-class representation geometry. We evaluate TaxoNet in open-world settings that capture co-occurring recognition challenges. Leveraging diverse plant datasets, including Google Auto-Arborist (urban tree imagery), iNaturalist (Plantae observations across heterogeneous ecosystems), and NAFlora-Mini (herbarium collections), we demonstrate that TaxoNet consistently outperforms strong baselines, including multimodal foundation models.
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。