Acoustic identification of individual animals with hierarchical contrastive learning

TL;DR

This paper introduces a hierarchical contrastive learning approach for acoustic identification of individual animals, improving accuracy by preserving taxonomic relationships and enabling open-set classification.

Contribution

It proposes hierarchy-aware loss functions for AIID, enhancing individual and taxonomic level accuracy and supporting open-set classification scenarios.

Findings

Hierarchical embeddings improve identification accuracy at multiple taxonomic levels.

Hierarchy-aware loss functions outperform non-hierarchical models.

The method effectively classifies novel individual classes in open-set scenarios.

Abstract

Acoustic identification of individual animals (AIID) is closely related to audio-based species classification but requires a finer level of detail to distinguish between individual animals within the same species. In this work, we frame AIID as a hierarchical multi-label classification task and propose the use of hierarchy-aware loss functions to learn robust representations of individual identities that maintain the hierarchical relationships among species and taxa. Our results demonstrate that hierarchical embeddings not only enhance identification accuracy at the individual level but also at higher taxonomic levels, effectively preserving the hierarchical structure in the learned representations. By comparing our approach with non-hierarchical models, we highlight the advantage of enforcing this structure in the embedding space. Additionally, we extend the evaluation to the classification of novel individual classes, demonstrating the potential of our method in open-set classification scenarios.