AI Paper Atlas

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

Unsupervised Domain Adaptive 3D Detection With Multi-Level Consistency

Zhipeng Luo, Zhongang Cai, Changqing Zhou, Gongjie Zhang, Haiyu Zhao, Shuai Yi, Shijian Lu, Hongsheng Li, Shanghang Zhang, Ziwei Liu

ICCV 2021 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 83 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 point-level box consistency loss (ablation)MLC-Net · KITTI->WaymoAP/L1: 18.61 -> 30.34Improved
add point-level class consistency loss (ablation)MLC-Net · KITTI->WaymoAP/L1: 18.61 -> 20.34Improved
add instance-level box consistency loss (ablation)MLC-Net · KITTI->WaymoAP/L1: 18.61 -> 33.21Improved
use all four consistency losses at two levels (ablation)MLC-Net · KITTI->WaymoAP/L1: 34.95 -> 38.21Improved
use replicated inputs for matching instead of nearest-point (ablation)MLC-Net · KITTI->WaymoAP/L1: 2.93 -> 38.21Improved
use replicated proposals instead of max-IoU box matching (ablation)MLC-Net · KITTI->WaymoAP/L1: 26.95 -> 38.21Improved
enable neural statistics-level consistency (teacher uses student running BN stats) (ablation)MLC-Net · KITTI->WaymoAP/L1: 2.79 -> 38.21Improved
enable neural statistics consistency instead of separate BN (ablation)MLC-Net · KITTI->WaymoAP/L1: 29.88 -> 38.21Improved
enable EMA update of teacher (ablation)MLC-Net · KITTI->WaymoAP/L1: 8.95 -> 38.21Improved
add input augmentation (ablation)MLC-Net · KITTI->WaymoAP/L1: 34.34 -> 36.23Improved
add both input and RoI augmentation (ablation)MLC-Net · KITTI->WaymoAP/L1: 34.34 -> 38.21Improved
MLC-Net versus Statistical Normalization with target size statisticsPointRCNN · KITTI->WaymoAP/L1: 30.69 -> 38.21Improved

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