Research map / Detection and segmentation / Weakly supervised detection and segmentation
Power of Cooperative Supervision: Multiple Teachers Framework for Advanced 3D Semi-Supervised Object Detection
Jin-Hee Lee, Jae-Keun Lee, Jeseok Kim, Kwon Soon
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add multiple category-specialized teachers (MPGen) instead of a single teacher (ablation) | 3D SSOD baseline · LiO 15% labeled | mAP: 51.7 -> 53.8 | Improved |
| add PieAug on top of MPGen (ablation) | MultipleTeachers · LiO 15% labeled | mAP: 53.8 -> 55.0 | Improved |
| set PieAug pie angle to 45 degrees instead of 15 degrees (ablation) | PieAug · 1% labeled | mAP: 53.0 -> 54.2 | Improved |
| increase PieAug pie angle from 45 to 60 degrees (ablation) | PieAug · 1% labeled | mAP: 54.2 -> 53.0 | Hurt |
| use PieAug instead of PolarMix (ablation) | MultipleTeachers · KITTI 1% labeled | mAP: 36.4 -> 64.6 | Improved |
| use PieAug instead of Shuffle Data augmentation (ablation) | MultipleTeachers · KITTI 1% labeled | mAP: 43.7 -> 64.6 | Improved |
| use PieAug instead of PseudoAugment (ablation) | MultipleTeachers · KITTI 1% labeled | mAP: 62.2 -> 64.6 | Improved |
| use PieAug instead of PseudoAugment (ablation) | MultipleTeachers · LiO 1% labeled | mAP: 39.0 -> 39.1 | No clear effect |
| use MultipleTeachers SSL instead of HSSDA with PV-RCNN | PV-RCNN · LiO 15% labeled | mAP: 49.1 -> 50.5 | Improved |
| use MultipleTeachers SSL instead of HSSDA with Re-VoxelDet | Re-VoxelDet · LiO 15% labeled | mAP: 58.8 -> 59.7 | Improved |
| use MultipleTeachers instead of HSSDA | Voxel-RCNN · LiO 1% labeled | mAP: 30.7 -> 37.8 | Improved |
| use MultipleTeachers instead of HSSDA | Voxel-RCNN · LiO 15% labeled | mAP: 53.7 -> 55.0 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 3DIoUMatch — 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection (CVPR 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Humble Teachers Teach Better Students for Semi-Supervised Object Detection (CVPR 2021 · similarity 0.87)
- Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection (CVPR 2023 · similarity 0.87)
- A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection (CVPR 2024 · similarity 0.87)
- Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection (CVPR 2025 · similarity 0.85)
- Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.85)
- Semi-supervised 3D Object Detection with PatchTeacher and PillarMix (AAAI 2024 · similarity 0.85)
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.
