Multi-label classification for multi-temporal, multi-spatial coral reef condition monitoring using vision foundation model with adapter learning

• URL: http://arxiv.org/abs/2503.23012v1
• Date: Sat, 29 Mar 2025 08:32:44 GMT
• Title: Multi-label classification for multi-temporal, multi-spatial coral reef condition monitoring using vision foundation model with adapter learning
• Authors: Xinlei Shao, Hongruixuan Chen, Fan Zhao, Kirsty Magson, Jundong Chen, Peiran Li, Jiaqi Wang, Jun Sasaki,
• Abstract summary: 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.
• Score: 20.74182654369854
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Coral reef ecosystems provide essential ecosystem services, but face significant threats from climate change and human activities. Although advances in deep learning have enabled automatic classification of coral reef conditions, conventional deep models struggle to achieve high performance when processing complex underwater ecological images. Vision foundation models, known for their high accuracy and cross-domain generalizability, offer promising solutions. However, fine-tuning these models requires substantial computational resources and results in high carbon emissions. To address these challenges, adapter learning methods such as Low-Rank Adaptation (LoRA) have emerged as a solution. This study introduces an approach integrating the DINOv2 vision foundation model with the LoRA fine-tuning method. The approach leverages multi-temporal field images collected through underwater surveys at 15 dive sites at Koh Tao, Thailand, with all images labeled according to universal standards used in citizen science-based conservation programs. 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. Furthermore, incorporating LoRA reduced the trainable parameters from 1,100M to 5.91M. Transfer learning experiments conducted under different temporal and spatial settings highlight the exceptional generalizability of DINOv2-LoRA across different seasons and sites. This study is the first to explore the efficient adaptation of foundation models for multi-label classification of coral reef conditions under multi-temporal and multi-spatial settings. The proposed method advances the classification of coral reef conditions and provides a tool for monitoring, conserving, and managing coral reef ecosystems.

Related papers

• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO) In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery. We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• 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)
• From underwater to aerial: a novel multi-scale knowledge distillation approach for coral reef monitoring [1.0644791181419937]
  This study presents a novel multi-scale approach to coral reef monitoring, integrating fine-scale underwater imagery with medium-scale aerial imagery.<n>A transformer-based deep-learning model is trained on underwater images to detect the presence of 31 classes covering various coral morphotypes, associated fauna, and habitats.<n>The results show that the multi-scale methodology successfully extends fine-scale classification to larger reef areas, achieving a high degree of accuracy in predicting coral morphotypes and associated habitats.
  arXiv  Detail & Related papers  (2025-02-25T06:12:33Z)
• Back Home: A Machine Learning Approach to Seashell Classification and Ecosystem Restoration [49.1574468325115]
  In Costa Rica, an average of 5 tons of seashells are extracted from ecosystems annually. Confiscated seashells, cannot be returned to their ecosystems due to the lack of origin recognition.<n>We developed a convolutional neural network (CNN) specifically for seashell identification.<n>We built a dataset from scratch, consisting of approximately 19000 images from the Pacific and Caribbean coasts.<n>The model has been integrated into a user-friendly application, which has classified over 36,000 seashells to date, delivering real-time results within 3 seconds per image.
  arXiv  Detail & Related papers  (2025-01-08T23:07:10Z)
• Automatic Coral Detection with YOLO: A Deep Learning Approach for Efficient and Accurate Coral Reef Monitoring [0.0]
  Coral reefs are vital ecosystems that are under increasing threat due to local human impacts and climate change. In this paper, we present an automatic coral detection system utilizing the You Only Look Once deep learning model.
  arXiv  Detail & Related papers  (2024-04-03T08:00:46Z)
• 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)
• Scalable Semantic 3D Mapping of Coral Reefs with Deep Learning [4.8902950939676675]
  This paper presents a new paradigm for mapping underwater environments from ego-motion video. We show high-precision 3D semantic mapping at unprecedented scale with significantly reduced required labor costs. Our approach significantly scales up coral reef monitoring by taking a leap towards fully automatic analysis of video transects.
  arXiv  Detail & Related papers  (2023-09-22T11:35:10Z)
• Pengembangan Model untuk Mendeteksi Kerusakan pada Terumbu Karang dengan Klasifikasi Citra [3.254879465902239]
  This study utilizes a specialized dataset consisting of 923 images collected from Flickr using the Flickr API. The method employed in this research involves the use of machine learning models, particularly convolutional neural networks (CNN) It was found that a from-scratch ResNet model can outperform pretrained models in terms of precision and accuracy.
  arXiv  Detail & Related papers  (2023-08-08T15:30:08Z)
• Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms [77.25251419910205]
  Harmful algal blooms (HABs) cause significant fish deaths in aquaculture farms. Currently, the standard method to enumerate harmful algae and other phytoplankton is to manually observe and count them under a microscope. We employ Generative Adversarial Networks (GANs) to generate synthetic images.
  arXiv  Detail & Related papers  (2022-08-03T20:15:55Z)
• 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)
• Deep learning for lithological classification of carbonate rock micro-CT images [52.77024349608834]
  This work intends to present an application of deep learning techniques to identify patterns in Brazilian pre-salt carbonate rock microtomographic images. Four convolutional neural network models were proposed. According to accuracy, Model 2 trained on resized images achieved the best results, reaching an average of 75.54% for the first evaluation approach and an average of 81.33% for the second.
  arXiv  Detail & Related papers  (2020-07-30T19:14:00Z)

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.