Spiking Point Transformer for Point Cloud Classification
This work addresses energy-efficient 3D point cloud classification for applications like robotics and autonomous systems, representing a novel integration rather than an incremental improvement.
The authors tackled the problem of applying spiking neural networks (SNNs) to 3D point cloud classification by introducing the Spiking Point Transformer (SPT), achieving state-of-the-art results on three benchmark datasets and reducing theoretical energy consumption by at least 6.4 times compared to artificial neural networks.
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.