AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Label-Guided Auxiliary Training Improves 3D Object Detector

Yaomin Huang, Xinmei Liu, Yichen Zhu, Zhiyuan Xu, Chaomin Shen, Zhengping Che, Guixu Zhang, Yaxin Peng, Feifei Feng, Jian Tang

ECCV 2022 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 15 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 LG3D auxiliary training to VoteNetVoteNet · SUN RGB-DmAP@0.25: 59.1 -> 61.7Improved
add LG3D to VoteNetVoteNet · ScanNetV2mAP@0.5: 39.9 -> 43.0Improved
add LG3D to GroupFree3DGroupFree3D · ScanNetV2mAP@0.25: 69.1 -> 70.9Improved
add LG3D to GroupFree3DGroupFree3D · SUN RGB-DmAP@0.5: 45.2 -> 47.5Improved
add LG3D to PointPillarsPointPillars · KITTI Car moderateAP_3d: 74.31 -> 76.42Improved
add LG3D to 3DSSD3DSSD · KITTI Car moderateAP_3d: 79.57 -> 81.47Improved
add LKM module to VoteNet baseline (ablation)VoteNet · ScanNetV2mAP@0.5: 39.9 -> 41.3Improved
add LAI module on top of LKM (ablation)VoteNet+LKM · ScanNetV2mAP@0.5: 41.3 -> 43.0Improved
use two-stage instead of one-stage training (ablation)VoteNet+LG3D · ScanNetV2mAP@0.5: 42.4 -> 43.0Improved
train VoteNet baseline for more epochs (36 -> 72) (ablation)VoteNet · ScanNetV2mAP@0.25: 62.90 -> 62.50No clear effect
train GroupFree3D baseline longer (80 -> 160 epochs) (ablation)GroupFree3D · ScanNetV2mAP@0.25: 69.10 -> 68.50No clear effect
add size augmentation and fake instances (ablation)VoteNet+LG3D · ScanNetV2mAP@0.25: 64.5 -> 65.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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