用Mamba替换YOLO26的注意力模块，提升效率几乎不丢精度。
MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26
- 用轻量级Mamba替代原模型中的C2PSA块，保持结构简洁。
- 参数减少2.9%，计算量降12.1%，CPU推理速度提至20 FPS（+17.6%）。
- 适合追求高效部署的轻量级目标检测场景，尤其在边缘设备上表现佳。
状态空间模型（SSMs），尤其是Mamba，因其线性计算复杂度，成为自注意力机制的高效替代方案。本文将Mamba引入最新的无NMS目标检测框架YOLO26，提出MambaPSA，作为主干网络末尾C2PSA模块的轻量级替代。为进一步优化性能，在颈部的P3、P4、P5层加入双向视觉Mamba（BiViM）模块。在PASCAL VOC 2007+2012数据集上的实验表明，使用MambaPSA使参数减少2.9%，计算量降低12.1%，且在几乎无精度损失（-0.1 mAP50:95）的前提下，实现CPU推理吞吐量提升17.6%（从17增至20 FPS）。P4层插入BiViM时取得最佳精度提升（+0.9 mAP50:95）。结果表明，将SSMs用于替代非NMS轻量级检测器中的注意力模块，可在效率与精度间实现良好权衡。
原文摘要 · Abstract (English)
State space models (SSMs), notably Mamba, have recently emerged as efficient alternatives to self-attention with linear computational complexity. We investigate the integration of Mamba into YOLO26, the latest non-maximum suppression (NMS)-free object detection framework, by proposing MambaPSA, a lightweight Mamba-based replacement for the C2PSA block at the end of the backbone. To complement this study, we additionally insert a bidirectional Vision Mamba (BiViM) module at the P3, P4, and P5 levels of the neck. Experiments on PASCAL VOC 2007+2012 show that MambaPSA reduces parameters by 2.9%, FLOPs by 12.1%, and improves CPU inference throughput by 17.6% (from 17 to 20 FPS) with negligible accuracy change (-0.1 mAP50:95), while the P4 BiViM placement yields the best accuracy gain (+0.9 mAP50:95). These results suggest that SSMs offer a favorable efficiency-accuracy trade-off when replacing attention-based blocks in NMS-free lightweight detectors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。