AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Learning from Noisy Data for Semi-Supervised 3D Object Detection

Zehui Chen, Zhenyu Li, Shuo Wang, Dengpan Fu, Feng Zhao

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection

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 noise-resistant (soft) classification supervision (ablation)NoisyStudent baseline · ONCE val (Small)mAP: 55.50 -> 56.80Improved
add Gaussian NLL regression on top of classification supervision (ablation)NoiseDet · ONCE val (Small)mAP: 56.80 -> 57.27Improved
add dense feature consistency constraint (ablation)NoiseDet · ONCE val (Small)mAP: 57.27 -> 58.01Improved
soft quality-based targets instead of Focal Loss on hard pseudo labels (ablation)classification supervision · ONCE val (Small)AP overall: 55.45 -> 56.80Improved
combine IoU and confidence by weighted sum instead of multiplication (ablation)classification target · ONCE val (Small)AP overall: 56.52 -> 56.80Improved
feature-level L2 consistency instead of label-level L2 (ablation)consistency regularization · ONCE val (Small)AP: 55.45 -> 56.70Improved
feature-level distance correlation instead of plain L2 (ablation)consistency regularization · ONCE val (Small)AP: 56.70 -> 56.07Hurt
Gaussian NLL regression loss instead of Smooth L1 or L1 (ablation)regression supervision · ONCE val (Small)mAP: 56.4 mAPImproved
replace NoisyStudent with NoiseDet on SECONDSECOND · ONCE val (Small)mAP: 55.50 -> 58.01Improved
replace NoisyStudent with NoiseDet on CenterPointCenterPoint · ONCE val (Small)mAP: 63.77 -> 65.57Improved
use higher-quality pseudo labels from CenterPoint-E teacherNoiseDet with SECOND student · ONCE valmAP: 58.00 -> 60.19Improved
increase amount of unlabeled data from Small to LargeNoiseDet · ONCE valmAP: 58.00 -> 61.16Improved

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