AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

DetMatch: Two Teachers Are Better than One for Joint 2D and 3D Semi-Supervised Object Detection

Jinhyung Park, Chenfeng Xu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 33 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
replace confidence thresholding with 2D-3D teacher matching (ablation)DetMatch · KITTI 1% 3DmAP: 54.4 -> 57.9Improved
add 2D-teacher/3D-student box consistency (ablation)DetMatch · KITTI 1% 3DmAP: 57.9 -> 59.4Improved
add 2D-teacher/3D-student class consistency (ablation)DetMatch · KITTI 1% 2DmAP: 69.8 -> 71.4Improved
use MSE instead of Focal loss for class consistency (ablation)DetMatch · KITTI 1% 3DmAP: 59.0 -> 58.2Hurt
set tau_hung to -1.5 instead of -1 or -2 (ablation)DetMatch · KITTI 1% 3DmAP: 54.2/52.4 -> 57.9Improved
remove COCO pre-training of 2D detector (ablation)DetMatch · KITTI 1% 2DmAP: 71.4 -> 59.1Hurt
remove COCO pre-training of 2D detector (ablation)DetMatch · KITTI 1% 3DPedestrian AP: 57.3 -> 55.3No clear effect
apply 2D confidence thresholding (Unbiased Teacher) SSLConfidence Thresholding · KITTI 1% 2DmAP: 65.3 -> 60.4Hurt
DetMatch over 3D confidence thresholdingDetMatch · KITTI 1% 3DPedestrian AP: 42.7 -> 57.3Improved
DetMatch over 3D confidence thresholdingDetMatch · Waymo 1% 3DCar L1 mAP: 52.6 -> 52.2Hurt
DetMatch over 3D confidence thresholdingDetMatch · Waymo 1% 3DPed L1 mAP: 35.2 -> 39.5Improved
swap PV-RCNN for SECONDDetMatch · KITTI 1% 3DmAP: 38.8 -> 49.4Improved

Later papers that compared with this method

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

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