MambaPSA：YOLO26中基于Mamba的C2PSA替代方案
MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26
浏览论文内容
中文总结 AI 辅助
研究将Mamba集成到YOLO26中，提出MambaPSA替代主干末端的C2PSA块，并在颈部插入BiViM模块。实验表明MambaPSA能减少参数和FLOP，提升CPU推理吞吐量，且精度变化小，P4 BiViM布局精度提升最佳，展现了SSMs在轻量级检测器中的效率-精度权衡。
中文摘要 AI 辅助
状态空间模型（SSMs），尤其是Mamba，最近成为具有线性计算复杂度的自注意力的有效替代方案。我们通过提出MambaPSA来研究将Mamba集成到YOLO26（最新的无非极大值抑制（NMS）目标检测框架）中，MambaPSA是一种轻量级的基于Mamba的主干末端C2PSA块的替代方案。为补充该研究，我们还在颈部的P3、P4和P5级别插入双向视觉Mamba（BiViM）模块。在PASCAL VOC 2007+2012上的实验表明，MambaPSA减少了2.9%的参数、12.1%的FLOP，在精度变化可忽略不计（-0.1 mAP50:95）的情况下将CPU推理吞吐量提高了17.6%（从17 FPS提高到20 FPS），而P4 BiViM布局产生了最佳的精度提升（+0.9 mAP50:95）。这些结果表明，在无NMS的轻量级检测器中替换基于注意力的块时，SSMs提供了良好的效率-精度权衡。
英文摘要
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.
发表机构
- Department of Electrical and Computer Engineering, Tamkang University（淡江大学电机与计算机工程学系）
机构由 AI 辅助整理，请以论文原文为准。
