LEMMA: Laplacian pyramids for Efficient Marine SeMAntic Segmentation

TL;DR

LEMMA is a lightweight marine semantic segmentation model that uses Laplacian Pyramids to improve edge detection, achieving high accuracy with significantly reduced computational costs suitable for real-time applications.

Contribution

The paper introduces LEMMA, a novel lightweight segmentation architecture leveraging Laplacian Pyramids for efficient marine environment analysis under resource constraints.

Findings

Achieves 93.42% IoU on Oil Spill dataset

Reduces model size and computation by up to 71x and 88.5% GFLOPs

Cuts inference time by up to 84.65%

Abstract

Semantic segmentation in marine environments is crucial for the autonomous navigation of unmanned surface vessels (USVs) and coastal Earth Observation events such as oil spills. However, existing methods, often relying on deep CNNs and transformer-based architectures, face challenges in deployment due to their high computational costs and resource-intensive nature. These limitations hinder the practicality of real-time, low-cost applications in real-world marine settings. To address this, we propose LEMMA, a lightweight semantic segmentation model designed specifically for accurate remote sensing segmentation under resource constraints. The proposed architecture leverages Laplacian Pyramids to enhance edge recognition, a critical component for effective feature extraction in complex marine environments for disaster response, environmental surveillance, and coastal monitoring. By integrating edge information early in the feature extraction process, LEMMA eliminates the need for computationally expensive feature map computations in deeper network layers, drastically reducing model size, complexity and inference time. LEMMA demonstrates state-of-the-art performance across datasets captured from diverse platforms while reducing trainable parameters and computational requirements by up to 71x, GFLOPs by up to 88.5\%, and inference time by up to 84.65\%, as compared to existing models. Experimental results highlight its effectiveness and real-world applicability, including 93.42\% IoU on the Oil Spill dataset and 98.97\% mIoU on Mastr1325.