MambaFPN: A SSM-based feature pyramid network for object detection.

Object detection is a fundamental task in computer vision, aiming to localize and classify objects within images. Feature pyramid networks (FPNs) play a crucial role in modern object detectors by constructing hierarchical multi-scale feature maps to effectively handle objects of varying sizes. However, most existing advanced FPN methods rely heavily on convolutional neural networks (CNNs), which struggle to capture global context information. To address this limitation, we propose leveraging vision mamba blocks to enhance global modeling capabilities. The vanilla vision mamba block, through its state space mechanism, enables global context modeling for every spatial pixel within a single feature map. Building on this, we first use vision mamba blocks to extract global information from individual feature maps in the hierarchy. Subsequently, additional vision mamba blocks facilitate inter-scale information exchange among multi-scale feature maps, ensuring comprehensive global context integration. The proposed method, termed MambaFPN, significantly enhances object detector performance. For instance, it improves the Average Precision (AP) of vanilla FPN from 38.6 to 39.4, with fewer parameters. This demonstrates the effectiveness and efficiency of MambaFPN in advancing object detection.