MATANet: A Multi-context Attention and Taxonomy-Aware Network for Fine-Grained Underwater Recognition of Marine Species

TL;DR

MATANet is a novel neural network that integrates environmental context and taxonomic hierarchy to improve fine-grained underwater marine species recognition, achieving state-of-the-art results on multiple datasets.

Contribution

It introduces a multi-context attention module and a hierarchical learning module to incorporate environmental and taxonomic information into marine species classification.

Findings

Achieves state-of-the-art accuracy on FathomNet2025, FAIR1M, and LifeCLEF2015-Fish datasets.

Effectively models environmental context and taxonomic hierarchy for better discrimination.

Demonstrates significant improvement over existing methods in underwater species recognition.

Abstract

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