Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference

TL;DR

This paper introduces hierarchy-aware multimodal learning methods for taxonomic inference, significantly improving biodiversity classification accuracy and robustness by encoding biological hierarchy and supporting flexible modality fusion.

Contribution

It presents two novel end-to-end models that incorporate hierarchical information and modality fusion, enhancing robustness and accuracy in biodiversity identification tasks.

Findings

Over 14% accuracy improvement over baselines

Significant gains under partial and corrupted DNA data

Enhanced robustness through hierarchy-aware embedding

Abstract

Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, the core task is taxonomic prediction - inferring order, family, genus, or species from imperfect inputs such as specimen images, DNA barcodes, or both. Existing multimodal methods often treat taxonomy as a flat label space and therefore fail to encode the hierarchical structure of biological classification, which is critical for robustness under noise and missing modalities. We present two end-to-end variants for hierarchy-aware multimodal learning: CLiBD-HiR, which introduces Hierarchical Information Regularization (HiR) to shape embedding geometry across taxonomic levels, yielding structured and noise-robust representations; and CLiBD-HiR-Fuse, which additionally trains a lightweight fusion predictor that supports image-only, DNA-only, or joint inference and is resilient to modality corruption. Across large-scale biodiversity benchmarks, our approach improves taxonomic classification accuracy by over 14 percent compared to strong multimodal baselines, with particularly large gains under partial and corrupted DNA conditions. These results highlight that explicitly encoding biological hierarchy, together with flexible fusion, is key for practical biodiversity foundation models.