Sparse Point-Guided Fusion of Supervised and Self-Supervised Learning Model for Seaweed Segmentation

• URL: http://arxiv.org/abs/2606.21026v1
• Date: Fri, 19 Jun 2026 01:28:43 GMT
• Title: Sparse Point-Guided Fusion of Supervised and Self-Supervised Learning Model for Seaweed Segmentation
• Abstract summary: Blue carbon ecosystems are recognized as important natural carbon sinks.<n>This paper addresses precise seaweed classification for blue carbon quantification in Ocean Digital Twin initiatives.<n>We propose a novel two-stage seaweed segmentation technique.
• Score: 0.9823973011876452
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The ocean plays a critical role in sustainable development, particularly in climate change mitigation. Among marine ecosystems, blue carbon ecosystems are recognized as important natural carbon sinks. In this context, this paper addresses precise seaweed classification for blue carbon quantification in Ocean Digital Twin initiatives. Conventional methods, including supervised learning (limited by data scarcity and domain gaps) and self-supervised learning (unable to assign class labels), struggle with underwater complexities and diverse seaweed species. To overcome this, we propose a novel two-stage seaweed segmentation technique. This technique first utilizes Supervised and Self-supervised Learning Model Propagation (SSL.Prop.), which leverages supervised learning for initial class information and approximate locations, guiding self-supervised learning for detailed, accurate segmentation. Subsequently, MaskFusion (MF) refines these results by merging instance-level masks for highly accurate segmentation. This integrated approach allows automatic class label assignment and mitigates domain gap effects. Specifically, instance segmentation estimates sparse point locations which then guide self-supervised learning for detailed region segmentation. Evaluated with underwater images from Yamaguchi Prefecture, our full proposed method (SSL.Prop.+MF) achieved a 0.068 mIoU improvement over USIS-SAM, demonstrating significant accuracy gains, particularly for small seaweed. This approach demonstrates strong potential for improving blue carbon quantification and marine ecosystem monitoring.

Related papers

• OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models [57.19693589926157]
  OceanPile is a large-scale multimodal corpus designed for ocean foundation models.<n>It comprises three key components: OceanCorpus, OceanInstruction, and OceanBenchmark.<n>All datasets are publicly released to advance the field of marine artificial intelligence.
  arXiv  Detail & Related papers  (2026-04-25T14:53:37Z)
• Exploring the Underwater World Segmentation without Extra Training [55.291219073365546]
  We introduce textbfAquaOV255, the first large-scale and fine-grained underwater segmentation dataset.<n>We also present textbfEarth2Ocean, a training-free OV segmentation framework.
  arXiv  Detail & Related papers  (2025-11-11T07:22:56Z)
• Deep Learning Models for Coral Bleaching Classification in Multi-Condition Underwater Image Datasets [0.0]
  Coral reefs support numerous marine organisms and are an important source of coastal protection from storms and floods.<n>This study presents a novel machine-learning-based coral bleaching classification system based on a diverse global dataset.<n>We benchmarked and compared three state-of-the-art models: Residual Neural Network (ResNet), Vision Transformer (ViT), and Convolutional Neural Network (CNN)
  arXiv  Detail & Related papers  (2025-10-24T06:13:15Z)
• Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset [76.92197418745822]
  camouflaged instance segmentation (CIS) faces greater challenges in accurately segmenting objects that blend closely with their surroundings.<n>Traditional camouflaged instance segmentation methods, trained on terrestrial-dominated datasets with limited underwater samples, may exhibit inadequate performance in underwater scenes.<n>We introduce the first underwater camouflaged instance segmentation dataset, UCIS4K, which comprises 3,953 images of camouflaged marine organisms with instance-level annotations.
  arXiv  Detail & Related papers  (2025-10-20T14:34:51Z)
• MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment [56.88334234553316]
  We introduce textbfMARIS (underlineMarine Open-Vocabulary underlineInstance underlineSegmentation), the first large-scale fine-grained benchmark for underwater Open-Vocabulary (OV) segmentation.<n>Our framework consistently outperforms existing OV baselines both In-Domain and Cross-Domain setting.
  arXiv  Detail & Related papers  (2025-10-17T07:50:58Z)
• The point is the mask: scaling coral reef segmentation with weak supervision [1.4286124121075066]
  Drone-based aerial imagery offers broad spatial coverage, its limited resolution makes it difficult to reliably distinguish fine-scale classes, such as coral morphotypes.<n>We present a multi-scale weakly supervised semantic segmentation framework that addresses this challenge by transferring fine-scale ecological information from underwater imagery to aerial data.<n>This study presents a scalable, cost-effective methodology for high-resolution reef monitoring, combining low-cost data collection, weakly supervised deep learning and multi-scale remote sensing.
  arXiv  Detail & Related papers  (2025-08-26T11:58:50Z)
• YH-MINER: Multimodal Intelligent System for Natural Ecological Reef Metric Extraction [23.4289262373633]
  Coral reefs, crucial for sustaining marine biodiversity and ecological processes, face escalating threats.<n>This study develops the YH-MINER system, establishing an intelligent framework for "object detection-semantic segmentation-prior input"<n>The system achieves genus-level classification accuracy of 88% and simultaneously extracting core ecological metrics.
  arXiv  Detail & Related papers  (2025-05-28T11:36:18Z)
• Unveiling 3D Ocean Biogeochemical Provinces in the North Atlantic: A Systematic Comparison and Validation of Clustering Methods [1.2932412290302258]
  Aim was to objectively define regions of the North Atlantic through systematic comparison of clustering methods.<n>About 300 million measured salinity, temperature, and oxygen, nitrate, phosphate and silicate concentration values served as input.<n>Results showed that UMAP-DBSCAN best represented the data.
  arXiv  Detail & Related papers  (2025-04-25T08:55:40Z)
• Multi-label classification for multi-temporal, multi-spatial coral reef condition monitoring using vision foundation model with adapter learning [20.74182654369854]
  This study introduces an approach integrating the DINOv2 vision foundation model with the LoRA fine-tuning method.<n>The experimental results demonstrate that the DINOv2-LoRA model achieved superior accuracy, with a match ratio of 64.77%, compared to 60.34% achieved by the best conventional model.
  arXiv  Detail & Related papers  (2025-03-29T08:32:44Z)
• Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater Environments [57.59857784298534]
  We propose an integrated pipeline that combines Visual Place Recognition (VPR), feature matching, and image segmentation on video-derived images.<n>This method enables robust identification of revisited areas, estimation of rigid transformations, and downstream analysis of ecosystem changes.
  arXiv  Detail & Related papers  (2025-03-06T05:13:19Z)
• SeagrassFinder: Deep Learning for Eelgrass Detection and Coverage Estimation in the Wild [1.0617118349563253]
  Seagrass meadows play a crucial role in marine ecosystems, providing benefits such as carbon sequestration, water quality improvement, and habitat provision.<n>Current manual methods of analyzing underwater video data to assess seagrass coverage are time-consuming and subjective.<n>This work explores the use of deep learning models to automate the process of seagrass detection and coverage estimation from underwater video data.
  arXiv  Detail & Related papers  (2024-12-20T18:50:54Z)
• DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation [44.99833362998488]
  We present DeepAqua, a self-supervised deep learning model that eliminates the need for manual annotations during the training phase. We exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 7%, Intersection Over Union by 27%, and F1 score by 14%.
  arXiv  Detail & Related papers  (2023-05-02T18:06:21Z)
• SALT: Sea lice Adaptive Lattice Tracking -- An Unsupervised Approach to Generate an Improved Ocean Model [72.3183990520267]
  We propose SALT: Sea lice Adaptive Lattice Tracking approach for efficient estimation of sea lice dispersion and distribution. Specifically, an adaptive spatial mesh is generated by merging nodes in the lattice graph of the Ocean Model based on local ocean properties. The proposed SALT technique shows promise for enhancing proactive aquaculture management through predictive modelling of sea lice infestation pressure maps in a changing climate.
  arXiv  Detail & Related papers  (2021-06-24T17:29:42Z)

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.