AI Paper Atlas

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

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

Huan-ang Gao, Beiwen Tian, Pengfei Li, Hao Zhao, Guyue Zhou

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 21 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 quantization error correction (QEC) (ablation)DQS3D · ScanNet v2 (20% labels), voxel 0.01mmAP@0.50: 47.1 -> 48.5Improved
add QEC at larger voxel size 0.03m (ablation)DQS3D · ScanNet v2 (20% labels), voxel 0.03mweighted IoU (%): 65.63 -> 68.12Improved
add box consistency loss (ablation)DQS3D · ScanNet v2 (20% labels)mAP@0.50: 45.3 -> 48.5Improved
add centerness consistency loss (ablation)DQS3D · ScanNet v2 (20% labels)mAP@0.50: 46.4 -> 48.5Improved
add class consistency loss (ablation)DQS3D · ScanNet v2 (20% labels)mAP@0.50: 47.3 -> 48.5Improved
use dense matching instead of sparse proposal matching (ablation)FCAF3D mean teacher · ScanNet v2 (20% labels)mAP@0.50: 44.2 -> 48.5Improved
apply dense matching to a different backbone (TR3D) (ablation)TR3D · ScanNet v2 (20% labels)mAP@0.50: 46.8 -> 49.9Improved
apply DQS3D self-training in the fully supervised settingFCAF3D · ScanNet v2 (100% labels)mAP@0.50: 55.1 -> 56.3Improved
apply DQS3D self-training in the fully supervised settingFCAF3D · SUN RGB-D (100% labels)mAP@0.50: 47.5 -> 48.2Improved
DQS3D vs 3DIoUMatch with 20% labelssemi-supervised 3D detection · ScanNet v2 (20% labels)mAP@0.50: 35.2 -> 48.5Improved

Later papers that compared with this method

1 later accepted paper reports DQS3D 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