RSMamba: Remote Sensing Image Classification With State Space Model

By Keyan Chen, Bo-Ying Chen, Chenyang Liu, Wenyuan Li, Zhengxia Zou, Zhenwei Shi. IEEE Geoscience and Remote Sensing Letters, 2024

371 citations recorded by the source corpus.

Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation. The recent advancements of convolutional neural networks (CNNs) and transformers have markedly enhanced classification accuracy. Nonetheless, remote sensing scene classification remains a significant challenge, especially given the complexity and diversity of remote sensing scenarios and the variability of spatiotemporal resolutions. The capacity for whole-image understanding can provide more precise semantic cues for scene discrimination. In this letter, we introduce RSMamba, a novel architecture for remote sensing image classification. RSMamba is based on the state space model (SSM) and incorporates an efficient, hardware-aware design known as the Mamba. It integrates the advantages of both a global receptive field and linear modeling complexity. To overcome the limitation of the vanilla Mamba, which can only model causal sequences and is not adaptable to 2-D image data, we propose a dynamic multipath activation mechanism to augment Mamba’s capacity to model noncausal data. Notably, RSMamba maintains the inherent modeling mechanism of the vanilla Mamba, yet exhibits superior performance across multiple remote sensing image classification datasets, e.g., F1 scores of 95.25, 92.63, and 95.18 on the UC Merced, AID, and RESISC45 classification datasets, respectively, exceeding those of concurrent Vim and VMamba. This indicates that RSMamba holds significant potential to function as the backbone of future visual foundation models. The code is available at https://github.com/KyanChen/RSMamba.

Subfields: Media Technology

View Paper: https://www.semanticscholar.org/paper/5f07ef98b64b2ab47105018cbda158527f903b28

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Media Technology

1. Lefei Zhang
2. Hongruixuan Chen
3. Bo Du
4. Yong Luo
5. Zengmao Wang
6. Chengxi Han
7. Yapeng Li
8. Naoto Yokoya

Citations in the corpus

• MambaHSI: Spatial–Spectral Mamba for Hyperspectral Image Classification (2025, background): “…from the strong long-range modeling capabilities while maintaining linear computational complexity, the Mamba has received substantial research across many fields, such as language understanding [22], [24], medical image analysis [17], [25], computer vision [19], [26], and so on [27], [28], [29].”
• ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model (2024, methodology): “Inspired by this progress, some pioneering work has introduced the Mamba architecture to the field of remote sensing image processing [48], [49].”