AI Paper Atlas

Research map / Point clouds / Point cloud classification

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition

Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Zhiwu Lu, Jun He, Xiaoyong Du

AAAI 2022 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 88 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
add both ASVT and CSVT sparse voxel transformersSVT-Net · U.S.average recall at top-1 (%): 86.7 -> 90.1Improved
add both ASVT and CSVT sparse voxel transformersSVT-Net · R.A.average recall at top-1 (%): 80.4 -> 84.3Improved
add both ASVT and CSVT sparse voxel transformersSVT-Net · B.D.average recall at top-1 (%): 81.5 -> 85.5Improved
add CSVT to ASVT-Net (ablation)SVT-Net · Oxfordaverage recall at top-1% (%): 98.0 -> 97.8No clear effect
add CSVT to ASVT-Net (ablation)SVT-Net · B.D.average recall at top-1% (%): 88.4 -> 90.7Improved
add ASVT to CSVT-Net (ablation)SVT-Net · B.D.average recall at top-1% (%): 89.5 -> 90.7Improved
use 4 tokens instead of 8 (ablation)SVT-Net · Oxfordaverage recall at top-1% (%): 97.8 -> 97.9No clear effect
use 6 tokens instead of 8 (ablation)SVT-Net · Oxfordaverage recall at top-1% (%): 97.8 -> 98.0No clear effect
use 10 tokens instead of 8 (ablation)SVT-Net · U.S.average recall at top-1 (%): 90.1 -> 87.2Hurt
reduce descriptor dimension to 128 (ablation)SVT-Net · R.A.average recall at top-1 (%): 84.3 -> 81.9Hurt
increase descriptor dimension to 384 (ablation)SVT-Net · R.A.average recall at top-1 (%): 84.3 -> 84.9Improved
increase descriptor dimension to 512 (ablation)SVT-Net · B.D.average recall at top-1% (%): 90.7 -> 88.2Hurt

Later papers that compared with this method

1 later accepted paper reports SVT-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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