AI Paper Atlas

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

Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance

Kuan-Chih Huang, Yi-Hsuan Tsai, Ming-Hsuan Yang

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 11 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 output-level 2D-3D box guidance (GIoU between projected 3D box and 2D box) (ablation)VG-W3D baseline · KITTI val Car AP3D Mod.AP3D: 74.00 -> 76.42Improved
Add training-level guidance (score-consistent pseudo-label refinement) (ablation)VG-W3D baseline · KITTI val Car AP3D Mod.AP3D: 74.00 -> 77.75Improved
Add feature-level objectness guidance alone (ablation)VG-W3D baseline · KITTI val Car AP3D Mod.AP3D: 74.00 -> 74.29Improved
Combine feature, output and training guidance (ablation)VG-W3D · KITTI val Car AP3D Mod.AP3D: 74.00 -> 78.89Improved
Use KL objectness loss with image branch instead of omitting the image-domain objectness (ablation)Feature-level guidance · KITTI val Car AP3D Mod.AP3D: 74.61 -> 76.71Improved
Use KL objectness distillation instead of L2 feature mimicking (ablation)Feature-level guidance · KITTI val Car AP3D Mod.AP3D: 75.69 -> 76.71Improved
Use self-supervised segmentation mask instead of 2D box mask for foreground supervision (ablation)Feature-level guidance · KITTI val Car AP3D Mod.AP3D: 74.65 -> 76.71Improved
Use GIoU loss instead of IoU loss for 2D-3D constraint (ablation)Output-level guidance · KITTI val Car AP3D Mod.AP3D: 74.50 -> 76.71Improved
Use GIoU loss instead of L1 corner regression (ablation)Output-level guidance · KITTI val Car AP3D Mod.AP3D: 74.70 -> 76.71Improved
Add 2D-box overlap filter and score filter to pseudo-labeling instead of plain pseudo-labeling (ablation)Training-level guidance · KITTI val Car AP3D Mod.AP3D: 76.64 -> 78.89Improved
Add overlap filter only to pseudo-labeling (ablation)Training-level guidance · KITTI val Car AP3D Mod.AP3D: 76.64 -> 77.55Improved
Run more pseudo-label self-training rounds (ablation)Training-level guidance · KITTI val pseudo-label recall IoU=0.7recall: 0.4671 -> 0.7422 after round 2, 0.7421 round 3Improved

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