.png){kind=icon}
返回
Marine Debris Segmentation Using a Parameter Efficient Octonion-Based Architecture
.png){kind=icon}
OA
AI
DOI：10.1109/LGRS.2023.3321177.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Marine debris poses a significant ecological challenge, necessitating advanced methods for its accurate detection and segmentation. Deep learning (DL) enables advanced remote sensing (RS) capabilities for earth observation, however, its on- board deployment is hindered by limitations in resource availability. In this letter, octonion neural networks (ONNs) are proposed for developing a parameter-efficient solution to address the problem of marine debris segmentation. ONNs extend the capabilities of real-valued networks by incorporating octonions, an 8-D hypercomplex number system. By harnessing the power of octonions, such as their ability to capture higher-dimensional relationships and extract robust feature representations, enhanced segmentation accuracy can be achieved. The proposed ONN model is evaluated on the marine debris archive (MARIDA) dataset, a comprehensive benchmark for marine debris segmentation. The results demonstrate that the proposed approach outperforms the state of the art, achieving remarkable improvements of 9.9% and 7.6% in terms of the intersection over union (IoU) and F1 metrics, respectively. Moreover, the ONN approach delivers performance similar to that of the real-valued architecture, while utilizing 1/13 of the network parameters.
Keyword:
Hypercomplex numbers
marine debris image segmentation
octonion neural networks (ONNs)
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
暂无机构信息
引用论文
Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better高效深度学习: 关于使深度学习模型更小、更快、更好的调查OAAI
OAAI分享收藏
When reduced fat increases preference. How fat reduction in nutrition tables and numeracy skills affect food choices.png)
Appetite
AppetiteIF0
PREAI
分享收藏Understanding the Pathogenesis of Red Mark Syndrome in Rainbow Trout (Oncorhynchus mykiss) through an Integrated Morphological and Molecular ApproachAnimalsOAAI
AnimalsIF0
OAAI分享收藏
查看更多内容