Marine Debris Segmentation Using a Parameter Efficient Octonion-Based Architecture

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.