Deep-Sea Fauna Segmentation: A Comparative Analysis of Convolutional and Vision Transformer Architectures at Lucky Strike Vent Field
Abstract. Due to recent technological developments, the acquisition and availability of deep-sea imagery has increased exponentially in the last years, leading to an increasing backlog in image annotation and processing, attributable to limited specialized human resources. In this work, we investigate the performance of well-established convolutional neural networks and Vision Transformer (ViT) based architectures, namely, DeepLabv3+ and UNETR, for the segmentation of fauna in deep-sea images. The dataset consists of images captured at the Lucky Strike Vent field, located on the mid-Atlantic ridge, of three edifices named Montsegur, White Castle, and Eiffel Tower. Our experimental investigation reveals that the Vision Transformer consistently outperforms the fully convolutional deep learning architecture, by approximately 14% in terms of F1-Score, demonstrating the effectiveness of ViTs in capturing intricate patterns and long-range dependencies present in deep-sea imagery. Our findings highlight the potential of ViTs as a promising approach for accurate semantic segmentation in challenging environmental contexts, paving the way for improved understanding and analysis of deep-sea ecosystems.
Authors
- Henrique Fagundes Gasparoto (ORCID: https://orcid.org/0000-0003-2061-7596)
- Giovanni Costa (ORCID: https://orcid.org/0000-0002-0656-2499)
- Gustavo Andrade-Miranda
- Thibault Napoléon (ORCID: https://orcid.org/0000-0001-5405-7705)
- Marjolaine Matabos (ORCID: https://orcid.org/0000-0003-1983-9896)
- Pedro Juan Soto Vega (ORCID: https://orcid.org/0000-0001-5396-8531)
- Ayoub Karine
- Panagiotis Papadakis (ORCID: https://orcid.org/0009-0006-8720-9107)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Ifremer (FR)
- Inserm (FR)
- Université de Bretagne Occidentale (FR)
- Université Paris Cité (FR)
- Institut Supérieur de l'Électronique et du Numérique (FR)
- Universidade do Estado do Rio de Janeiro (BR)
- Laboratoire des Sciences et Techniques de l’Information de la Communication et de la Connaissance (FR)
- IMT Atlantique (FR)
- LIP6 (FR)
- Laboratoire de Traitement de l'Information Médicale (FR)
Publication Details
- Journal
- ISPRS annals of the photogrammetry, remote sensing and spatial information sciences
- Published
- 2024-11-04
- DOI
- https://doi.org/10.5194/isprs-annals-x-3-2024-387-2024
- Primary Topic
- Underwater Acoustics Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Institut Français de Recherche pour l'Exploitation de la Mer
- European Commission
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro
- Centre National de la Recherche Scientifique