AI Paper Atlas

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

Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection

Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao

CVPR 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 29 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 Bi3D with 1% target annotation budget instead of ST3D with SNPV-RCNN · nuScenes→KITTIAP_BEV: 84.29 -> 87.00Improved
Use Bi3D with 1% target annotation budget instead of ST3D with SNPV-RCNN · Waymo→KITTIAP_3D: 76.86 -> 78.03Improved
Increase target annotation budget from 1% to 5%Bi3D with SN · nuScenes→KITTIAP_BEV: 87.00 -> 89.63Improved
Add domainness-aware active source sampling instead of random source sampling (ablation)Bi3D with SN and random target sampling · nuScenes→KITTIAP_BEV: 84.42 -> 85.02Improved
Add diversity-based active target sampling instead of random target sampling (ablation)Bi3D with SN and random source sampling · nuScenes→KITTIAP_BEV: 84.42 -> 86.53Improved
Use active sampling for both source and target rather than random sampling for both (ablation)Bi3D with SN · Waymo→KITTIAP_BEV: 85.48 -> 87.12Improved
Remove SN (ablation)Bi3D · nuScenes→KITTIAP_3D: 77.55 -> 71.56Hurt
Combine objectness and entropy scores for foreground-aware discriminator features (ablation)Bi3D source-and-target sampling · Waymo→KITTIAP_3D: 76.69 -> 78.03Improved
Increase selected source proportion from 1% to 25% (ablation)Bi3D · Waymo→nuScenesAP_BEV: 86.95 -> 85.24Hurt
Combine Bi3D active annotation with ST3D pseudo-labeling of remaining target data (ablation)PV-RCNN · nuScenes→KITTIAP_BEV: 87.00 -> 89.28Improved

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