ReefNet: A Large-Scale, Taxonomically Enriched Dataset and Benchmark for Hard Coral Classification

ICLR 2026 Conference Submission21326 Authors

Keywords: Reef Ecology, Scleractinian Corals, Hard Corals, Marine Science, Coral Classification, Image Dataset, Benchmarking

TL;DR: ReefNet introduces a large-scale, taxonomically enriched dataset and benchmark for hard coral classification, demonstrating global applicability through rigorous model benchmarking.

Abstract: Coral reefs are rapidly declining due to anthropogenic pressures like climate change, underscoring the urgent need for scalable, automated monitoring. We introduce ReefNet, a large public coral reef image dataset with point-label annotations mapped to the World Register of Marine Species (WoRMS). ReefNet aggregates imagery from 76 curated CoralNet sources and an additional site from Al-Wajh in the Red Sea, totaling (925 K) genus-level hard coral annotations with expert-verified labels. Unlike prior datasets, often limited by size, geography, or coarse labels and not ML-ready, ReefNet offers fine-grained, taxonomically mapped labels at a global scale to WoRMS. We propose two evaluation settings: (i) a within-source benchmark that partitions each source’s images for localized evaluation, and (ii) a cross-source benchmark that withholds entire sources to test domain generalization. We analyze both supervised and zero-shot classification performance on ReefNet, and find that while supervised within-source performance is promising, supervised performance drops sharply across domains, and performance is low across the board for zero-shot models, especially for rare and visually similar genera, providing a challenging benchmark intended to catalyze advances in domain generalization and fine-grained coral classification. We will release our dataset, benchmarking code, and pretrained models to advance robust, domain-adaptive, global coral reef monitoring and conservation.

Primary Area: datasets and benchmarks

Submission Number: 21326