轻量级3D目标检测模型，适合在设备端高效运行。
StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloud
- 用条带注意力模块捕捉长距离空间依赖，计算复杂度从二次降至线性。
- 仅0.65M参数，汽车检测mAP达79.97%，参数量仅为PointPillars的1/7。
- 适合边缘设备部署，兼顾精度与效率，优于同类轻量化方法。
点云3D目标检测模型因计算和内存需求大，难以部署。为此，我们提出StripDet，一种专为设备端高效设计的轻量级框架。首先，提出新颖的条带注意力块（SAB），通过将标准2D卷积分解为非对称条带卷积，高效提取方向特征，将计算复杂度从二次降低至线性。其次，设计硬件友好的分层主干网络，结合深度可分离卷积与简单多尺度融合策略，实现端到端高效。在KITTI数据集上实验验证了其优越性：仅0.65M参数，汽车检测mAP达79.97%，相比基准模型PointPillars参数减少7倍。此外，StripDet超越近期轻量化及知识蒸馏方法，在精度-效率权衡上表现更优，成为边缘设备上实际可行的3D检测方案。
原文摘要 · Abstract (English)
The deployment of high-accuracy 3D object detection models from point cloud remains a significant challenge due to their substantial computational and memory requirements. To address this, we introduce StripDet, a novel lightweight framework designed for on-device efficiency. First, we propose the novel Strip Attention Block (SAB), a highly efficient module designed to capture long-range spatial dependencies. By decomposing standard 2D convolutions into asymmetric strip convolutions, SAB efficiently extracts directional features while reducing computational complexity from quadratic to linear. Second, we design a hardware-friendly hierarchical backbone that integrates SAB with depthwise separable convolutions and a simple multiscale fusion strategy, achieving end-to-end efficiency. Extensive experiments on the KITTI dataset validate StripDet's superiority. With only 0.65M parameters, our model achieves a 79.97% mAP for car detection, surpassing the baseline PointPillars with a 7x parameter reduction. Furthermore, StripDet outperforms recent lightweight and knowledge distillation-based methods, achieving a superior accuracy-efficiency trade-off while establishing itself as a practical solution for real-world 3D detection on edge devices.
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。