WaterSAM: Adapting SAM for Underwater Object Segmentation

Object segmentation, a key type of image segmentation, focuses on detecting and delineating individual objects within an image, essential for applications like robotic vision and augmented reality. Despite advancements in deep learning improving object segmentation, underwater object segmentation re...

Full description

Saved in:
Bibliographic Details
Published in:Journal of marine science and engineering 2024-09, Vol.12 (9), p.1616
Main Authors: Hong, Yang, Zhou, Xiaowei, Hua, Ruzhuang, Lv, Qingxuan, Dong, Junyu
Format: Article
Language:English
Subjects:
Accuracy
Adaptation
Archaeology
Architecture
Augmented Reality
Biological effects
Computer applications
Computer vision
Computing costs
Datasets
Decomposition
Deep learning
Electromagnetic absorption
Environmental monitoring
Image contrast
Image enhancement
Image processing
Image segmentation
Light absorption
Machine vision
Marine biology
Medical imaging equipment
Neural networks
Parameters
Segment Anything Model (SAM)
Semantics
Turbulence
Underwater
Underwater exploration
underwater image
underwater object segmentation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Object segmentation, a key type of image segmentation, focuses on detecting and delineating individual objects within an image, essential for applications like robotic vision and augmented reality. Despite advancements in deep learning improving object segmentation, underwater object segmentation remains challenging due to unique underwater complexities such as turbulence diffusion, light absorption, noise, low contrast, uneven illumination, and intricate backgrounds. The scarcity of underwater datasets further complicates these challenges. The Segment Anything Model (SAM) has shown potential in addressing these issues, but its adaptation for underwater environments, AquaSAM, requires fine-tuning all parameters, demanding more labeled data and high computational costs. In this paper, we propose WaterSAM, an adapted model for underwater object segmentation. Inspired by Low-Rank Adaptation (LoRA), WaterSAM incorporates trainable rank decomposition matrices into the Transformer’s layers, specifically enhancing the image encoder. This approach significantly reduces the number of trainable parameters to 6.7% of SAM’s parameters, lowering computational costs. We validated WaterSAM on three underwater image datasets: COD10K, SUIM, and UIIS. Results demonstrate that WaterSAM significantly outperforms pre-trained SAM in underwater segmentation tasks, contributing to advancements in marine biology, underwater archaeology, and environmental monitoring.
ISSN:2077-1312
2077-1312
DOI:10.3390/jmse12091616