AI Paper Atlas

Research map / Point clouds / Point cloud classification

Spiking PointNet: Spiking Neural Networks for Point Clouds

Dayong Ren, Zhe Ma, Yuanpei Chen, Weihang Peng, Xiaode Liu, Yuhan Zhang, Yufei Guo

NeurIPS 2023 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with 1 time step and infer with 4 instead of training with 4 time steps (ablation)Spiking PointNet · ModelNet40accuracy: 86.70% -> 87.13%Improved
train with 1 time step and infer with 4 instead of training with 4 time steps (ablation)Spiking PointNet · ModelNet10accuracy: 91.05% -> 92.32%Improved
infer with multiple time steps instead of 1 (trained 1 T) (ablation)Spiking PointNet · ModelNet40accuracy: 86.98% -> 87.26%Improved
add membrane potential perturbation (ablation)Spiking PointNet · ModelNet40accuracy: 87.13% -> 88.61%Improved
add membrane potential perturbation (ablation)Spiking PointNet · ModelNet10accuracy, test 1 T: 91.99% -> 91.66%Hurt
add membrane potential perturbation (ablation)Spiking PointNet · ModelNet10accuracy, test 4 T: 92.32% -> 93.31%Improved
use surrogate k=5 instead of k=0.5 or k=20 (ablation)Spiking PointNet · ModelNet40accuracy, 1 time step: 80.34% / 83.46% -> 86.98%Improved
increase training time steps from 1 to 4 at k=5 (ablation)Spiking PointNet · ModelNet40accuracy: 86.98% -> 86.70%No clear effect
increase training time steps from 1 to 4 at k=20 (ablation)Spiking PointNet · ModelNet40accuracy: 83.46% -> 75.36%Hurt
average outputs across all time steps instead of using a single step (ablation)Spiking PointNet (train 4 T) · ModelNet40accuracy: 85.70% -> 86.70%Improved
replace PointNet ANN with Spiking PointNet 1 T (MPP)PointNet · ModelNet10energy per forward pass: 1.4 x 10^8 pJ -> 9.2 x 10^6 pJImproved
replace ANN PointNet with Spiking PointNet 4 T (MPP)PointNet · ModelNet40accuracy: 89.20% -> 88.61%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy