AI Paper Atlas

Research map / Point clouds / Point cloud classification

SpikeNet: Sparse Spike-Driven Mask Vector Transformer for Energy-Efficient and Stable Spiking Point Cloud Processing

Zhiming Zhou, Yong He, Chaoxu Mu, Qiaoyun Wu, Ajmal Saeed Mian

ICML 2026 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures

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
use DSSR before AMP and SVMT after AMP instead of the reverse order (ablation)SpikeNet · ModelNet40OA (%): 92.7 -> 93.4Improved
add SVMT to a DSSR-only encoder (second position) (ablation)SpikeNet · ModelNet40OA (%): 92.2 -> 93.4Improved
add DSSR to an SVMT-only encoder (first position) (ablation)SpikeNet · ModelNet40OA (%): 92.0 -> 93.4Improved
replace plain spiking MLP blocks with DSSR and SVMT (ablation)SpikeNet · ModelNet40OA (%): 90.1 -> 93.4Improved
spiking DSSR+SVMT versus ANN Conv-BN-ReLU blocks (ablation)SpikeNet · ModelNet40OA (%): 92.7 -> 93.4Improved
use Channel Masker instead of Npoint Masker in SPM (ablation)SpikeNet · ModelNet40OA (%): 93.2 -> 93.4Improved
use subtraction instead of summation as attention operator tau (ablation)SpikeNet-C · ModelNet40OA (%): 93.2 -> 93.4Improved
use subtraction instead of division as attention operator tau (ablation)SpikeNet-C · ModelNet40OA (%): 92.7 -> 93.4Improved
use subtraction instead of Hadamard product as attention operator tau (ablation)SpikeNet-C · ModelNet40OA (%): 93.0 -> 93.4Improved
increase time steps from 1 to 3 (ablation)SpikeNet-C · ModelNet40OA (%): 92.8 -> 93.4Improved
increase time steps from 3 to 4 (ablation)SpikeNet-C · ModelNet40OA (%): 93.4 -> 93.2Hurt
increase embedding dimension from 64 to 128 (ablation)SpikeNet-C · ModelNet40OA (%): 93.4 -> 92.9Hurt

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