Research map / Detection and segmentation / Weakly supervised detection and segmentation
Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection
Chuxin Wang, Wenfei Yang, Tianzhu Zhang
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 |
|---|---|---|---|
| replace deterministic box parameterization with side-aware parameterization alone (ablation) | VoteNet semi-supervised · ScanNet 20% | mAP50: 30.12 -> 30.42 | No clear effect |
| add soft pseudo-label selection using distribution variance (ablation) | VoteNet semi-supervised · ScanNet 20% | mAP50: 30.42 -> 33.28 | Improved |
| add side-aware uncertainty estimation module with geometric and distribution features (ablation) | VoteNet semi-supervised · ScanNet 20% | mAP50: 33.28 -> 37.29 | Improved |
| combine geometric features with distribution properties instead of either alone (ablation) | Uncertainty estimation module · ScanNet 20% | mAP50: 36.41 -> 37.29 | Improved |
| use side-aware parameterization instead of naive center/size parameterization (ablation) | VoteNet semi-supervised · ScanNet 20% | mAP50: 32.66 -> 37.29 | Improved |
| make regression probabilistic with side-aware parameterization (ablation) | VoteNet semi-supervised · ScanNet 20% | mAP50: 35.02 -> 37.29 | Improved |
| add side-aware weight assignment (ablation) | Soft-PLS · ScanNet 20% | mAP50: 35.79 -> 37.29 | Improved |
| add category-specific adaptive thresholds (ablation) | Soft-PLS · ScanNet 20% | mAP50: 35.21 -> 35.79 | Improved |
| add IoU-guided NMS with low-half strategy (ablation) | Soft-PLS · ScanNet 20% | mAP50: 30.42 -> 35.21 | Improved |
| raise pseudo-label thresholds to higher values (ablation) | Soft-PLS · ScanNet 20% | mAP50: 37.29 -> 34.73 | Hurt |
| lower pseudo-label thresholds (ablation) | Soft-PLS · ScanNet 20% | mAP50: 37.29 -> 36.91 | No clear effect |
| apply the method with 100% labeled data (copy as unlabeled) | VoteNet · ScanNet 100% | mAP50: 36.0 -> 44.1 | 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 10 of 10 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
- SA3Det++: Side-Aware Quality Estimation for Semi-Supervised 3D Object Detection (TPAMI 2025 · similarity 0.94)
- Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.90)
- Semi-supervised 3D Object Detection with PatchTeacher and PillarMix (AAAI 2024 · similarity 0.89)
- Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection (CVPR 2025 · similarity 0.89)
- Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.88)
- Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection (CVPR 2024 · similarity 0.87)
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.
