InsectMamba is a novel approach for insect pest classification that integrates State Space Models (SSMs), Convolutional Neural Networks (CNNs), Multi-Head Self-Attention (MSA), and Multilayer Perceptrons (MLPs) within Mix-SSM blocks. This integration leverages the strengths of each encoding strategy to extract comprehensive visual features, enhancing the model's ability to discern pest characteristics. A selective module is proposed to adaptively aggregate these features, improving the model's performance. The method was evaluated on five insect pest classification datasets, demonstrating superior performance compared to existing models. Ablation studies verified the significance of each component in the model, highlighting the effectiveness of the proposed architecture in addressing the challenges of pest camouflage and species diversity.InsectMamba is a novel approach for insect pest classification that integrates State Space Models (SSMs), Convolutional Neural Networks (CNNs), Multi-Head Self-Attention (MSA), and Multilayer Perceptrons (MLPs) within Mix-SSM blocks. This integration leverages the strengths of each encoding strategy to extract comprehensive visual features, enhancing the model's ability to discern pest characteristics. A selective module is proposed to adaptively aggregate these features, improving the model's performance. The method was evaluated on five insect pest classification datasets, demonstrating superior performance compared to existing models. Ablation studies verified the significance of each component in the model, highlighting the effectiveness of the proposed architecture in addressing the challenges of pest camouflage and species diversity.