CountMamba: Exploring Multi-directional Selective State-Space Models for Plant Counting

TL;DR

CountMamba introduces a multi-directional state-space model for plant counting, simulating human-like sequential scanning to improve accuracy across various plant types.

Contribution

It proposes a novel multi-directional state-space approach with adaptive feature fusion for more effective plant counting in high-resolution images.

Findings

Achieves competitive results on maize tassels, wheat ears, and sorghum heads.

Demonstrates the effectiveness of multi-directional scanning in plant counting.

Outperforms existing methods in accuracy and robustness.

Abstract

Plant counting is essential in every stage of agriculture, including seed breeding, germination, cultivation, fertilization, pollination yield estimation, and harvesting. Inspired by the fact that humans count objects in high-resolution images by sequential scanning, we explore the potential of handling plant counting tasks via state space models (SSMs) for generating counting results. In this paper, we propose a new counting approach named CountMamba that constructs multiple counting experts to scan from various directions simultaneously. Specifically, we design a Multi-directional State-Space Group to process the image patch sequences in multiple orders and aim to simulate different counting experts. We also design Global-Local Adaptive Fusion to adaptively aggregate global features extracted from multiple directions and local features extracted from the CNN branch in a sample-wise manner. Extensive experiments demonstrate that the proposed CountMamba performs competitively on various plant counting tasks, including maize tassels, wheat ears, and sorghum head counting.