首个面向点云分类的脉冲神经网络变压器，能效提升6.4倍。
Spiking Point Transformer for Point Cloud Classification
- 用队列驱动采样编码保留关键点，降低计算开销。
- 提出混合动态脉冲神经元，避免神经元过度依赖。
- 在三个数据集上达先进性能，能效比传统模型高6.4倍。
脉冲神经网络（SNN）因其稀疏二值激活，具备低功耗优势。尽管在2D图像处理中展现潜力，其在3D点云领域的应用仍不充分。为此，我们提出首个基于Transformer的SNN框架——脉冲点云变压器（SPT），用于点云分类。首先设计了队列驱动的采样直接编码方法，在每时刻保留最有效的支持点，降低计算成本；引入混合动态积分-发放神经元（HD-IF），模拟选择性神经元激活，减少对特定人工神经元的依赖。SPT在涵盖真实与合成数据的三个基准数据集上达到领先水平。理论分析表明，其能耗至少比对应人工神经网络（ANN）低6.4倍。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) offer an attractive and energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their sparse binary activation. When SNN meets Transformer, it shows great potential in 2D image processing. However, their application for 3D point cloud remains underexplored. To this end, we present Spiking Point Transformer (SPT), the first transformer-based SNN framework for point cloud classification. Specifically, we first design Queue-Driven Sampling Direct Encoding for point cloud to reduce computational costs while retaining the most effective support points at each time step. We introduce the Hybrid Dynamics Integrate-and-Fire Neuron (HD-IF), designed to simulate selective neuron activation and reduce over-reliance on specific artificial neurons. SPT attains state-of-the-art results on three benchmark datasets that span both real-world and synthetic datasets in the SNN domain. Meanwhile, the theoretical energy consumption of SPT is at least 6.4$\times$ less than its ANN counterpart.
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。