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

• URL: http://arxiv.org/abs/2510.16822v1
• Date: Sun, 19 Oct 2025 13:18:44 GMT
• Title: ReefNet: A Large scale, Taxonomically Enriched Dataset and Benchmark for Hard Coral Classification
• Authors: Yahia Battach, Abdulwahab Felemban, Faizan Farooq Khan, Yousef A. Radwan, Xiang Li, Fabio Marchese, Sara Beery, Burton H. Jones, Francesca Benzoni, Mohamed Elhoseiny,
• Abstract summary: We introduce ReefNet, a large public coral reef image dataset with point-label annotations mapped to the World Register of Marine Species (WoRMS)<n>ReefNet aggregates imagery from 76 curated CoralNet sources and an additional site from Al Wajh in the Red Sea.<n>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.
• Score: 32.33672517443114
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coral reefs are rapidly declining due to anthropogenic pressures such as 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 approximately 925000 genus-level hard coral annotations with expert-verified labels. Unlike prior datasets, which are often limited by size, geography, or coarse labels and are 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. This provides 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.

Related papers

• UKANFormer: Noise-Robust Semantic Segmentation for Coral Reef Mapping via a Kolmogorov-Arnold Network-Transformer Hybrid [4.147037463809748]
  We propose a novel se-mantic segmentation model to achieve high-precision mapping under noisy supervision.<n>UKANFormer incorporates a Global-Local Transformer (GL-Trans) block in the decoder, enabling the extraction of both global semantic structures and local boundary details.<n>In experiments, UKANFormer achieved a coral-class IoU of 67.00% and pixel accuracy of 83.98%, outperforming conventional baselines under the same noisy labels setting.
  arXiv  Detail & Related papers  (2025-10-19T06:51:03Z)
• The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs [4.096374910845255]
  We release the first general-purpose dense semantic segmentation dataset for coral reefs, covering 2075 images, 39 benthic classes, and 174k segmentation masks annotated by experts.<n>We benchmark a wide range of semantic segmentation models, and find that transfer learning from Coralscapes to existing smaller datasets consistently leads to state-of-the-art performance.<n>Coralscapes will catalyze research on efficient, scalable, and standardized coral reef surveying methods based on computer vision, and holds the potential to streamline the development of underwater ecological robotics.
  arXiv  Detail & Related papers  (2025-03-25T18:33:59Z)
• CoralSCOP-LAT: Labeling and Analyzing Tool for Coral Reef Images with Dense Mask [20.267378309290116]
  CoralSCOP-LAT is a coral reef image analysis and labeling tool that automatically segments and analyzes coral regions.<n>Our evaluations demonstrate that CoralSCOP-LAT surpasses existing coral reef analysis tools in terms of time efficiency, accuracy, precision, and flexibility.
  arXiv  Detail & Related papers  (2024-10-27T13:26:44Z)
• Deep learning for multi-label classification of coral conditions in the Indo-Pacific via underwater photogrammetry [24.00646413446011]
  This study created a dataset representing common coral conditions and associated stressors in the Indo-Pacific. It assessed existing classification algorithms and proposed a new multi-label method for automatically detecting coral conditions and extracting ecological information. The proposed method accurately classified coral conditions as healthy, compromised, dead, and rubble.
  arXiv  Detail & Related papers  (2024-03-09T14:42:16Z)
• CoralVOS: Dataset and Benchmark for Coral Video Segmentation [12.434773034255455]
  We propose a large-scale coral video segmentation dataset: textbfCoralVOS as demonstrated in Fig. 1. We perform experiments on our CoralVOS dataset, including 6 recent state-of-the-art video object segmentation (VOS) algorithms. The results show that there is still great potential for further promoting the segmentation accuracy.
  arXiv  Detail & Related papers  (2023-10-03T10:45:37Z)
• GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models [60.48306899271866]
  We present a new framework, called GREAT Score, for global robustness evaluation of adversarial perturbation using generative models. We show high correlation and significantly reduced cost of GREAT Score when compared to the attack-based model ranking on RobustBench. GREAT Score can be used for remote auditing of privacy-sensitive black-box models.
  arXiv  Detail & Related papers  (2023-04-19T14:58:27Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
  We present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers. Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
  arXiv  Detail & Related papers  (2021-08-29T05:45:03Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)
• Fine-Grained Visual Classification with Efficient End-to-end Localization [49.9887676289364]
  We present an efficient localization module that can be fused with a classification network in an end-to-end setup. We evaluate the new model on the three benchmark datasets CUB200-2011, Stanford Cars and FGVC-Aircraft.
  arXiv  Detail & Related papers  (2020-05-11T14:07:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.