AtrousMamaba: An Atrous-Window Scanning Visual State Space Model for Remote Sensing Change Detection

TL;DR

This paper introduces AtrousMamba, a novel model that balances local detail extraction and global context understanding in remote sensing change detection, outperforming existing methods on multiple benchmarks.

Contribution

It proposes the Atrous-window selective scan mechanism within the Mamba framework to enhance local feature extraction while maintaining global context integration.

Findings

Outperforms CNN, Transformer, and Mamba-based methods on six datasets.

Effectively captures long-range dependencies and local details.

Demonstrates superior accuracy in change detection tasks.

Abstract

Recently, a novel visual state space (VSS) model, referred to as Mamba, has demonstrated significant progress in modeling long sequences with linear complexity, comparable to Transformer models, thereby enhancing its adaptability for processing visual data. Although most methods aim to enhance the global receptive field by directly modifying Mamba's scanning mechanism, they tend to overlook the critical importance of local information in dense prediction tasks. Additionally, whether Mamba can effectively extract local features as convolutional neural networks (CNNs) do remains an open question that merits further investigation. In this paper, We propose a novel model, AtrousMamba, which effectively balances the extraction of fine-grained local details with the integration of global contextual information. Specifically, our method incorporates an atrous-window selective scan mechanism, enabling a gradual expansion of the scanning range with adjustable rates. This design shortens the distance between adjacent tokens, enabling the model to effectively capture fine-grained local features and global context. By leveraging the atrous window scan visual state space (AWVSS) module, we design dedicated end-to-end Mamba-based frameworks for binary change detection (BCD) and semantic change detection (SCD), referred to as AWMambaBCD and AWMambaSCD, respectively. Experimental results on six benchmark datasets show that the proposed framework outperforms existing CNN-based, Transformer-based, and Mamba-based methods. These findings clearly demonstrate that Mamba not only captures long-range dependencies in visual data but also effectively preserves fine-grained local details.