AI Paper Atlas

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

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

Zhuoxiao Chen, Yadan Luo, Zheng Wang, Mahsa Baktashmotlagh, Zi Huang

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 28 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 cross-domain examination (CDE) to pseudo-label filtering (ablation)ReDB · Waymo -> KITTI (Moderate)mAP 3D: 47.66 -> 50.10Improved
add OBC-based diversity downsampling (ablation)ReDB · Waymo -> KITTI (Moderate)mAP 3D: 47.07 -> 50.10Improved
add source ground-truth object sampling to target point clouds (ablation)ReDB baseline without sampling · Waymo -> KITTI (Moderate)mAP 3D: 42.26 -> 45.21Improved
add target pseudo-label sampling to target point clouds (ablation)ReDB baseline without sampling · Waymo -> KITTI (Moderate)mAP 3D: 42.26 -> 46.04Improved
source GT sampling alone improves easy level much more than moderate and hard (ablation)ReDB baseline · Waymo -> KITTImAP 3D: Easy 48.41 -> 54.10; Moderate 42.26 -> 45.21; Hard 40.18 -> 42.42Mixed
replace ST3D++ with ReDB on PointRCNN backbonePointRCNN · nuScenes -> KITTI (Moderate)average AP 3D: 36.58 -> 45.05Improved
replace ST3D++ with ReDB on large environmental gapSECOND · nuScenes -> KITTI (Moderate)mean AP 3D: 21.64 -> 26.11Improved
increase downsampling rate d to 10 (ablation)ReDB · Waymo -> KITTImAP 3D: -1.37% mAP3D, -2.57% mAP BEVHurt
vary CDE IoU threshold between 0.3 and 0.6 (ablation)ReDB · Waymo -> KITTImAP 3D and BEV: 2.69% and 2.07% fluctuationNo clear effect
ReDB versus SN on Waymo -> KITTI car and pedestrian 3D APReDB · Waymo -> KITTI (Moderate)Car AP 3D: SN 54.14 vs ReDB 54.12Mixed

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