MambaSOD: Small Object Detection from Drone Perspective in a Mamba-based Query-Feature Interaction Framework

Drone-perspective small object detection requires processing high-resolution imagery where objects typically occupy fewer than 32×32 pixels, demanding both fine-grained spatial preservation and global context modeling under strict computational constraints. Convolutional neural networks are limited by local receptive fields and cannot effectively model global context, while Transformerbased approaches, despite their global modeling capability, suffer from O(N 2 ) computational complexity that becomes a severe bottleneck when processing high-resolution inputs. This paper proposes MambaSOD, an end-to-end detection framework with an encoder-decoder architecture based on state space models that achieves linear computational complexity throughout the entire pipeline of feature extraction, multi-scale fusion, and query interaction. On the encoder side, MambaSOD builds a linear-complexity multi-scale representation by coupling a Vision Mamba backbone with a P2 high-resolution enhancement module, which recovers fine-grained texture details through dual-path fusion of shallow image features and up-sampled backbone output, together with a BiFPN that performs weighted bidirectional fusion across five scales. On the decoder side, we replace both self-attention and crossattention with Mamba-driven query interaction: the Mamba-based Query Self-Interaction (MQSI) module enables implicit interquery communication through bidirectional state propagation at O(N q ) cost, while the Mamba-based Query-Feature Interaction (MQFI) module reformulates query-feature cross-attention as a sequence modeling problem, reducing its complexity from O(N q ×N) to O(N q + N). Experiments on the VisDrone2019 and UAVDT datasets demonstrate that MambaSOD achieves 23.8% AP, a 52.6% relative improvement over the Vision Mamba baseline, while requiring fewer FLOPs than state-of-the-art detectors such as Cascade R-CNN, ViT, Deformable DETR, and DINO, offering a competitive accuracy-computation trade-off for high-resolution drone-perspective small object detection. Our code is available at https://github.com/LeoHoW6/MambaSOD-Drone-view-smallobject- detection-via-a-Mamba-based-query-feature-interaction-framework.git.