[Submitted on 19 Oct 2025 (v1), last revised 6 Nov 2026 (this version, v4)]
Authors:Abdulwahab Felemban, Yahia Battach, Faizan Farooq Khan, Yuqian Fu, Xuhui Liu, Yesmeen M. Khattab, Yousef A. Radwan, Xiang Li, Natalie Dunn, Susanne Bähr, Tullia Isotta Terraneo, Fabio Marchese, Sara Beery, Luis Silva, Rhonda Suka, Karla Gonzalez Martinez, Marta Ezeta Watts, Federica Barreca, Nicolas Oury, Burton H. Jones, Francesca Benzoni, Mohamed Elhoseiny
Abstract:Coral reef monitoring requires scalable recognition of visually similar taxa across heterogeneous underwater surveys. We introduce ReefNet, a public dataset that aligns approximately 925K hard-coral point annotations from 76 CoralNet sources and an independently collected Al-Wajh dataset with the World Register of Marine Species taxonomy. A stratified expert audit of 8,962 patches guides filtering to a 479,027-annotation benchmark with 39 labels: 38 genera and the family Fungiidae. Expert agreement is 92% on the retained audit subset, rather than an exhaustive accuracy estimate. We evaluate pretrained models through zero-shot recognition, few-shot adaptation, and full fine-tuning, each on within-source ReefNet and held-out-source Al-Wajh tests. Biological vision-language pretraining provides the strongest zero-shot results; supervised adaptation substantially improves recognition, with DINOv2 reaching 65.79% macro recall on Al-Wajh. Matched text-description experiments improve all four evaluated MLLMs on Al-Wajh, while a GPT-5.4 reasoning ablation does not improve over direct classification. Long-tail recognition, label uncertainty, and geographic imbalance remain challenges. ReefNet provides a taxonomically grounded resource for studying these challenges; the Al-Wajh test is a regional stress test rather than evidence of global robustness. Public data and resource links are documented in the supplement.
Submission history
From: Abdulwahab Felemban [view email]
[v1] Sun, 19 Oct 2025 13:18:44 UTC (24,046 KB)
[v2] Mon, 24 Nov 2025 14:18:04 UTC (23,832 KB)
[v3] Tue, 21 Apr 2026 13:18:32 UTC (4,392 KB)
[v4] Fri, 6 Nov 2026 10:34:35 UTC (5,798 KB)
