AI Paper Atlas

Research map / Point clouds / Point cloud classification

Masked Discrimination for Self-Supervised Learning on Point Clouds

Haotian Liu, Mu Cai, Yong Jae Lee

ECCV 2022 · Point clouds › Point cloud classification · approach: Masked point autoencoders · 180 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 MaskPoint pretraining vs scratchPointViT · ModelNet40OA: 91.4 -> 93.8Improved
add MaskPoint pretraining vs scratchPointViT · ScanObjectNN PBOA: 77.2 -> 84.6Improved
replace Point-BERT pretraining with MaskPointPointViT · ScanObjectNN PBOA: 83.1 -> 84.6Improved
replace OcCo pretraining with MaskPointPointViT · ModelNet40OA: 92.1 -> 93.8Improved
add MaskPoint pretraining on part segmentationPointViT · ShapeNetPartinstance mIoU: 85.1 -> 86.0Improved
add MaskPoint pretraining to 3DETR3DETR · ScanNet detectionAP25 / AP50: +1.3AP25 and +2.7AP50Improved
add Point-BERT pretraining to 3DETR3DETR · ScanNet detectionAP25: 62.1 -> 61.0No clear effect
increase 3DETR encoder layers from 3 to 12 with MaskPoint3DETR · ScanNet detectionAP25 / AP50: +2.1AP25 and +4.2AP50Improved
raise mask ratio from 0.25 to 0.90 (random) (ablation)MaskPoint · ScanObjectNN PBOA: 83.2 -> 84.6Improved
use random masking instead of block masking at 0.90 (ablation)MaskPoint · ScanObjectNN PBOA: 84.1 -> 84.6Improved
use 256 decoder queries instead of 64 (ablation)MaskPoint · ScanObjectNN PBOA: 83.7 -> 84.6Improved
increase decoder queries from 256 to 1024 (ablation)MaskPoint · ScanObjectNN PBOA: 84.6 -> 83.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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