OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space Model

TL;DR

OSDMamba introduces a novel Mamba-based architecture for oil spill detection in remote sensing images, effectively addressing class imbalance and small object detection issues, and achieving state-of-the-art results.

Contribution

This paper presents the first Mamba-based model tailored for oil spill detection, enhancing receptive fields and multi-scale feature fusion to improve detection accuracy.

Findings

Achieves 8.9% and 11.8% improvements in OSD metrics.

Effectively detects small oil spill areas.

Outperforms existing CNN-based methods.

Abstract

Semantic segmentation is commonly used for Oil Spill Detection (OSD) in remote sensing images. However, the limited availability of labelled oil spill samples and class imbalance present significant challenges that can reduce detection accuracy. Furthermore, most existing methods, which rely on convolutional neural networks (CNNs), struggle to detect small oil spill areas due to their limited receptive fields and inability to effectively capture global contextual information. This study explores the potential of State-Space Models (SSMs), particularly Mamba, to overcome these limitations, building on their recent success in vision applications. We propose OSDMamba, the first Mamba-based architecture specifically designed for oil spill detection. OSDMamba leverages Mamba's selective scanning mechanism to effectively expand the model's receptive field while preserving critical details. Moreover, we designed an asymmetric decoder incorporating ConvSSM and deep supervision to strengthen multi-scale feature fusion, thereby enhancing the model's sensitivity to minority class samples. Experimental results show that the proposed OSDMamba achieves state-of-the-art performance, yielding improvements of 8.9% and 11.8% in OSD across two publicly available datasets.