Fine-grained classification of marine animals supports ecology, biodiversity and habitat conservation, and evidence-based policy-making. However, existing methods often overlook contextual interactions from the surrounding environment and insufficiently incorporate the hierarchical structure of marine biological taxonomy. To address these challenges, we propose MATANet (Multi-context Attention and Taxonomy-Aware Network), a novel model designed for fine-grained marine species classification. MATANet mimics expert strategies by using taxonomy and environmental context to interpret ambiguous features of underwater animals. It consists of two key components: a Multi-Context Environmental Attention Module (MCEAM), which learns relationships between regions of interest (ROIs) and their surrounding environments, and a Hierarchical Separation-Induced Learning Module (HSLM), which encodes taxonomic hierarchy into the feature space. MATANet combines instance and environmental features with taxonomic structure to enhance fine-grained classification. Experiments on the FathomNet2025, FAIR1M, and LifeCLEF2015-Fish datasets demonstrate state-of-the-art performance. The source code is available at: https://github.com/dhlee-work/fathomnet-cvpr2025-ssl

翻译：海洋动物的细粒度分类对生态学、生物多样性保护、栖息地保育以及循证决策制定具有重要支撑作用。然而，现有方法往往忽略来自周围环境的上下文交互作用，且未能充分融入海洋生物分类学的层次结构。为应对这些挑战，我们提出了MATANet（多上下文注意力与分类感知网络），这是一种专为细粒度海洋物种分类设计的新型模型。MATANet通过利用分类学知识和环境上下文来解析水下动物的模糊特征，从而模拟专家策略。它包含两个关键组件：多上下文环境注意力模块（MCEAM），用于学习感兴趣区域（ROIs）与其周围环境之间的关系；以及层次分离诱导学习模块（HSLM），用于将分类学层次结构编码到特征空间中。MATANet将实例特征、环境特征与分类学结构相结合，以增强细粒度分类性能。在FathomNet2025、FAIR1M和LifeCLEF2015-Fish数据集上的实验证明了其最先进的性能。源代码可在以下网址获取：https://github.com/dhlee-work/fathomnet-cvpr2025-ssl