AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

Zhaoqi Leng, Shuyang Cheng, Benjamin Caine, Weiyue Wang, Xiao Zhang, Jonathon Shlens, Mingxing Tan, Dragomir Anguelov

ECCV 2022 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 18 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 PseudoFrame (drop low-confidence boxes and their points) instead of plain pseudo labelingPseudo labeling, PointPillars · Waymo val Vehicle 10%L1 AP: 50.7 -> 51.1Improved
add PseudoBBox and PseudoBackground on top of PseudoFrame (ablation)PseudoFrame, PointPillars · Waymo val 10%AP: +3.2 on Vehicle AP and + 1.2 on Pedestrian APImproved
replace pseudo labeling with all PseudoAugmentsPointPillars student · Waymo val Vehicle 10%L1 AP: 50.7 -> 54.3Improved
replace pseudo labeling with all PseudoAugmentsPointPillars student · Waymo val Pedestrian 10%L1 AP: 56.7 -> 58.4Improved
use PseudoAugments instead of pseudo labeling for a larger Pillars2X studentPillars2X · Waymo val Vehicle 10%AP: 51.6 -> 55.7Improved
use PseudoAugments instead of pseudo labeling when distilling to point-based StarNetStarNet · Waymo val Vehicle 10%AP: 48.2 -> 51.2Improved
use PseudoAugments instead of pseudo labeling on KITTI (moderate vehicle)PointPillars · KITTI val Vehicle moderate 10%AP: 51.4 -> 56.5Improved
use AutoPseudoAugment instead of PPBA at 10% labeledPointPillars · Waymo val Vehicle 10%AP L1: 50.2 -> 56.7Improved
use AutoPseudoAugment instead of pseudo labeling at 50% labeledPointPillars · Waymo val Pedestrian 50%AP L1: 68.2 -> 69.6Improved
use pseudo labeling instead of PPBA at 50% labeledPointPillars · Waymo val Vehicle 50%AP L1: 60.9 -> 59.8Hurt
add PseudoBBox instead of ground-truth box pasting (GTBBox) (ablation)PointPillars · Waymo val Vehicle 10%L1 AP: 44.7 -> 46.4Improved
add PseudoBackground versus PseudoBBox for pedestrians (ablation)PointPillars · Waymo val Pedestrian 10%L1 AP: PseudoBackground +3.1 AP vs PseudoBBox +1.2 APImproved

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