Research
MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26
arXiv:2607.12681v1 Announce Type: new Abstract: State space models (SSMs), notably Mamba, have recently emerged as efficient alternatives to self-attention with linear computational complexity. We inv
arXiv:2607.12681v1 Announce Type: new Abstract: 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.
Related
- Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
- Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR
- An approach with Visual and Tabular Mamba to multimodal medical data using Mixed Fusion
- Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution
- Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation
Source: arXiv cs.CV | 2026-07-15