Hierarchical Classification for Automated Image Annotation of Coral Reef Benthic Structures (Papers Track)

Celia Blondin (IRD); Joris Guerin (IRD, Univ. Montpellier); Laure Berti-Equille (IRD); Guilherme Ortigara Longo (Universidade Federal do Rio Grande do Norte); Kelly Inagaki (Universidade Federal do Rio Grande do Norte)

Paper PDF NeurIPS 2024 Recorded Talk Cite
Oceans & Marine Systems

Abstract

Automated benthic image annotation is crucial to efficiently monitor and protect coral reefs against climate change. Current machine learning approaches fail to capture the hierarchical nature of benthic organisms covering reef substrata, i.e., coral taxonomic levels and health condition. To address this limitation, we propose to annotate benthic images using hierarchical classification. Experiments on a custom dataset from a Northeast Brazilian coral reef show that our approach outperforms flat classifiers, improving both F1 and hierarchical F1 scores by approximately 2\% across varying amounts of training data. In addition, this hierarchical method aligns more closely with ecological objectives.