AI Paper Atlas

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

Transferable Semi-Supervised 3D Object Detection From RGB-D Data

Yew Siang Tang, Gim Hee Lee

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 39 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
use relaxed reprojection loss with upper bound 1.5x instead of direct reprojection loss (ablation)Ours + R · SUN-RGBD val CC semi-supervisedmAP: 25.6 -> 37.2Improved
enlarge the reprojection upper bound from 1.5x to 2.0x (ablation)Ours + R · SUN-RGBD val CC semi-supervisedmAP: 37.2 -> 30.8Hurt
add the BoxPC classification objective to the BoxPC Fit network (ablation)Ours + BoxPC · SUN-RGBD val CC semi-supervisedmAP: 32.1 -> 40.6Improved
add the BoxPC regression objective to the BoxPC Fit network (ablation)Ours + BoxPC · SUN-RGBD val CC semi-supervisedmAP: 39.8 -> 40.6Improved
use combined box-point cloud input representation instead of independent features (ablation)Ours + BoxPC · SUN-RGBD val CC semi-supervisedmAP: 34.4 -> 40.6Improved
remove the one-hot class vector from the baselineFPN* · SUN-RGBD val CC semi-supervisedmAP: 24.5 -> 30.1Improved
add relaxed reprojection loss and BoxPC Fit network to the baseline (ablation)FPN* w/o OneHot · SUN-RGBD val CC semi-supervisedmAP: 30.1 -> 41.1Improved
add box prior loss P (ablation)Ours + BoxPC + R · SUN-RGBD val CC semi-supervisedmAP: 41.1 -> 41.8Improved
add BoxPC + R + P to the baseline on CarsFPN · KITTI val CC semi-supervisedAP: 0.07% -> 59.95%Improved
add BoxPC + R + P to the baseline on PedestriansFPN · KITTI val CC semi-supervisedAP: 48.03% -> 67.49%Improved
add BoxPC + R + P to the baseline on CyclistsFPN · KITTI val CC semi-supervisedAP: 41.89% -> 51.83%Improved
add BoxPC Refine to fully-supervised FPN*FPN* · SUN-RGBD val fully-supervisedmAP: 51.5 -> 53.2Improved

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