这篇论文用分层损失和贝叶斯推理搞定水下物种分类，在FathomNet上只比第一名差3%，思路很实在。
针对水下图像中海洋物种自动分类面临的域迁移、细粒度相似性和标注粒度不均衡问题，研究者提出了一种结合分类学层次结构的深度学习框架。该方法包括分类学加权损失、最小风险贝叶斯推理、多尺度特征编码和独立的分层分类头。在FathomNet 2025数据集（包含7个分类等级的79个海洋类别）上评估，系统实现了1.581的平均分类学距离，接近第一名方案（1.535），差距在3%以内。主要改进来自于与度量对齐的推理以及简单解耦组件，它们在分布变化下比学习依赖关系具有更好的泛化能力。
Taxonomy-aware deep learning for hierarchical marine species classification in underwater imagery
Automated classification of marine species from underwater imagery is essential for scalable ocean biodiversity monitoring and conservation policy. Existing approaches struggle with severe domain shift across collection platforms, fine-grained visual similarity between closely related species, and uneven annotation granularity, where many specimens can only be identified to genus or a coarser taxonomic rank. We present a taxonomy-aware deep learning framework that aligns both the training loss and the inference rule with the hierarchical structure of biological classification, combining a taxonomy-weighted loss, minimum-risk Bayesian inference, multi-scale feature encoding, and independent per-rank classification heads. Evaluated on the FathomNet 2025 dataset1 (79 marine classes across seven taxonomic ranks), the system achieves a mean taxonomic distance of 1.581, within 3% of the 1st-place solution (1.535), with the largest gains from metric-aligned inference and simple, decoupled components that generalize better than learned dependencies under distribution shift.