Mamba-MOC: A Multicategory Remote Object Counting via State Space Model

TL;DR

Mamba-MOC introduces a novel mamba-based network for multicategory remote object counting, effectively capturing global and local context with improved efficiency, achieving state-of-the-art results in large-scale remote sensing scenarios.

Contribution

This paper is the first to apply the Mamba model to remote sensing object counting, integrating a cross-scale interaction module and a context state space model for enhanced accuracy.

Findings

Achieves state-of-the-art performance on large-scale remote sensing datasets.

Effectively models global and local contextual information.

Demonstrates computational efficiency over Transformer-based methods.

Abstract

Multicategory remote object counting is a fundamental task in computer vision, aimed at accurately estimating the number of objects of various categories in remote images. Existing methods rely on CNNs and Transformers, but CNNs struggle to capture global dependencies, and Transformers are computationally expensive, which limits their effectiveness in remote applications. Recently, Mamba has emerged as a promising solution in the field of computer vision, offering a linear complexity for modeling global dependencies. To this end, we propose Mamba-MOC, a mamba-based network designed for multi-category remote object counting, which represents the first application of Mamba to remote sensing object counting. Specifically, we propose a cross-scale interaction module to facilitate the deep integration of hierarchical features. Then we design a context state space model to capture both global and local contextual information and provide local neighborhood information during the scan process. Experimental results in large-scale realistic scenarios demonstrate that our proposed method achieves state-of-the-art performance compared with some mainstream counting algorithms.