Hierarchical Deep Learning for Diatom Image Classification: A Multi-Level Taxonomic Approach

TL;DR

This paper presents a hierarchical deep learning model for diatom image classification that improves accuracy at all taxonomic levels and ensures errors are taxonomically localized, enhancing interpretability and biological relevance.

Contribution

Introduction of DiatomCascadeNet, a hierarchical neural network architecture that jointly predicts multiple taxonomic levels and leverages hierarchy-aware training for improved accuracy and error localization.

Findings

Matches flat models at species level (69.4% accuracy)

Outperforms at higher taxonomic levels

Reduces mean taxonomic distance by 38.2%

Abstract

Accurate taxonomic identification of diatoms is essential for aquatic ecosystem monitoring, yet conventional methods depend heavily on expert taxonomists. Recent deep learning approaches improve automation, but most treat diatom recognition as flat classification, predicting only one taxonomic rank. We investigate whether embedding taxonomic hierarchy into neural network architectures can improve both accuracy and error locality. We introduce DiatomCascadeNet (H-COFGS), a hierarchical convolutional network with five cascaded heads that jointly predict class, order, family, genus, and species. Each head receives shared backbone features and probability distributions from higher levels, with binary masks restricting predictions to valid descendants during training and inference. Using a filtered dataset of 1,456 diatom images covering 82 species, we compare hierarchical and flat models under identical settings. H-COFGS matches flat baselines at the species level (69.4% accuracy) while outperforming at all upper taxonomic levels. When species predictions fail, errors remain taxonomically local: 92.5% of misclassified species are correctly predicted at the genus level, versus 67.2% for flat baselines. H-COFGS reduces mean taxonomic distance by 38.2% (1.209 vs. 1.955). Progressive training reveals bidirectional mechanisms: hierarchical constraint masks operate top-down to constrain prediction space, while gradients from fine-grained levels propagate bottom-up through the shared backbone, refining features. This improves class accuracy from 96.2% to 99.5% and yields 6-8% gains at upper levels, producing more robust, interpretable, and biologically aligned predictions for multi-level taxonomic classification.