AI Paper Atlas

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

StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-Based 3D Object Detection

Zhe Liu, Xiaoqing Ye, Xiao Tan, Errui Ding, Xiang Bai

AAAI 2023 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 15 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 response-level XGD and CLD to the stereo detector (ablation)DSGN with Improved LIGA features · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: +2.72 / +6.65 / +1.41Improved
Add XGD without CLD (ablation)Improved LIGA · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: 86.62 -> 86.78 (Car Easy); 40.11 -> 45.37 (Pedestrian Moderate)Improved
Add CLD without XGD (ablation)Improved LIGA · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: 67.03 -> 67.57; 40.11 -> 40.69; 40.90 -> 41.65Improved
Use center, size, and angle components together rather than one component alone (ablation)XGD · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: 67.84 / 44.11 / 41.18 -> 69.75 / 46.76 / 42.31Mixed
Use center component only for XGD (ablation)XGD · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: 68.22 / 46.33 / 42.19Mixed
Use all positive anchors rather than confidence-filtered high-quality boxes (ablation)XGD · KITTI validation, moderate Cars and Pedestrians3D AP: 67.72 / 43.65 -> 69.75 / 46.76Improved
Distill all foreground positions rather than only positive-anchor positions (ablation)CLD · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: 67.66 / 45.71 / 42.32 -> 69.75 / 46.76 / 42.31Mixed
Aggregate anchors at each position into a unified distribution instead of treating anchors separately (ablation)CLD · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: 67.74 / 46.18 / 40.69 -> 69.75 / 46.76 / 42.31Improved
Replace LIGA with StereoDistill response-level distillationDSGN · KITTI validation, moderate Car/Pedestrian/Cyclist3D mAP: 48.20 -> 50.12Improved
Add feature-based distillation and response-based distillation together (ablation)DSGN · KITTI validation, moderate Car/Pedestrian/CyclistMean 3D AP: 42.60 -> 52.94Improved
Distill with XGD and CLD using PointPillars as the LiDAR teacherLIGA and Improved LIGA · KITTI validation, moderate Car/Pedestrian/Cyclist3D AP: +1.28 / +2.09 / +1.84; +1.30 / +3.35 / +1.72Improved
Use StereoDistill instead of LIGADSGN · Argoverse validation, Car and Pedestrian3D AP: 34.37 -> 37.55; 10.76 -> 13.70Improved

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