ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908981505556480 |
|---|---|
| author | Felemban, Abdulwahab Battach, Yahia Khan, Faizan Farooq Fu, Yuqian Liu, Xuhui Khattab, Yesmeen M. Radwan, Yousef A. Li, Xiang Marchese, Fabio Beery, Sara Jones, Burton H. Benzoni, Francesca Elhoseiny, Mohamed |
| author_facet | Felemban, Abdulwahab Battach, Yahia Khan, Faizan Farooq Fu, Yuqian Liu, Xuhui Khattab, Yesmeen M. Radwan, Yousef A. Li, Xiang Marchese, Fabio Beery, Sara Jones, Burton H. Benzoni, Francesca Elhoseiny, Mohamed |
| contents | Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated monitoring. Progress in data-driven coral analysis, however, is constrained by the scarcity of large-scale datasets with fine-grained labels that are taxonomically consistent across sites and studies. To address this gap, we introduce ReefNet, a large-scale public coral reef image dataset with point-level annotations mapped to the World Register of Marine Species (WoRMS) taxonomy. ReefNet aggregates imagery from 76 curated CoralNet sources and an additional reef site from Al-Wajh (Red Sea), totaling approximately 925K genus-level hard coral annotations. Through expert-driven verification and targeted filtering, we derive a high-confidence benchmark subset with 92% expert agreement over 39 hard-coral label classes, enabling reliable evaluation under realistic label noise and strong class imbalance. Beyond dataset construction, we establish a comprehensive benchmark spanning zero-shot, cross-domain few-shot adaptation, within-source evaluation, and cross-source transfer to the Al-Wajh dataset. Experiments with state-of-the-art vision-language models (VLMs), multimodal large language models (MLLMs), and vision-only backbones reveal substantial degradation in zero-shot and extremely few-shot regimes, while adaptation with in-domain supervision yields large gains yet still leaves a persistent gap under cross-source shift and on long-tail genera. These results highlight fundamental challenges in applying general-purpose multimodal models to biodiversity monitoring and underscore the importance of large-scale, taxonomically grounded, high-quality datasets. ReefNet serves as both a benchmark and a training resource for advancing fine-grained coral reef understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16822 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition Felemban, Abdulwahab Battach, Yahia Khan, Faizan Farooq Fu, Yuqian Liu, Xuhui Khattab, Yesmeen M. Radwan, Yousef A. Li, Xiang Marchese, Fabio Beery, Sara Jones, Burton H. Benzoni, Francesca Elhoseiny, Mohamed Computer Vision and Pattern Recognition Artificial Intelligence Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated monitoring. Progress in data-driven coral analysis, however, is constrained by the scarcity of large-scale datasets with fine-grained labels that are taxonomically consistent across sites and studies. To address this gap, we introduce ReefNet, a large-scale public coral reef image dataset with point-level annotations mapped to the World Register of Marine Species (WoRMS) taxonomy. ReefNet aggregates imagery from 76 curated CoralNet sources and an additional reef site from Al-Wajh (Red Sea), totaling approximately 925K genus-level hard coral annotations. Through expert-driven verification and targeted filtering, we derive a high-confidence benchmark subset with 92% expert agreement over 39 hard-coral label classes, enabling reliable evaluation under realistic label noise and strong class imbalance. Beyond dataset construction, we establish a comprehensive benchmark spanning zero-shot, cross-domain few-shot adaptation, within-source evaluation, and cross-source transfer to the Al-Wajh dataset. Experiments with state-of-the-art vision-language models (VLMs), multimodal large language models (MLLMs), and vision-only backbones reveal substantial degradation in zero-shot and extremely few-shot regimes, while adaptation with in-domain supervision yields large gains yet still leaves a persistent gap under cross-source shift and on long-tail genera. These results highlight fundamental challenges in applying general-purpose multimodal models to biodiversity monitoring and underscore the importance of large-scale, taxonomically grounded, high-quality datasets. ReefNet serves as both a benchmark and a training resource for advancing fine-grained coral reef understanding. |
| title | ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.16822 |