Research map / Detection and segmentation / 3D detection and driving
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use Mean Teacher self-ensembling with the SESS perturbation and consistency framework instead of supervised VoteNet | VoteNet · SUN RGB-D val, 10% labeled | mAP@0.25: 34.43±1.07 -> 42.87±1.01 | Helped |
| Use Mean Teacher self-ensembling with the SESS perturbation and consistency framework instead of supervised VoteNet | VoteNet · ScanNetV2 val, 10% labeled | mAP@0.25: 30.97±0.79 -> 39.67±0.91 | Helped |
| Add size-aware consistency to center- and class-aware consistency (ablation) | SESS · SUN RGB-D val, 10% labeled | mAP@0.25: 40.0 -> 40.7 | Helped |
| Add size-aware consistency to center- and class-aware consistency (ablation) | SESS · ScanNetV2 val, 30% labeled | mAP@0.25: 51.5 -> 52.0 | Helped |
| Add class-aware consistency to center- and size-aware consistency (ablation) | SESS · SUN RGB-D val, 10% labeled | mAP@0.25: 38.9 -> 40.7 | Helped |
| Add class-aware consistency to center- and size-aware consistency (ablation) | SESS · ScanNetV2 val, 30% labeled | mAP@0.25: 50.5 -> 52.0 | Helped |
| Add center-aware consistency to class- and size-aware consistency (ablation) | SESS · SUN RGB-D val, 10% labeled | mAP@0.25: 40.3 -> 40.7 | Helped |
| Add center-aware consistency to class- and size-aware consistency (ablation) | SESS · ScanNetV2 val, 30% labeled | mAP@0.25: 50.7 -> 52.0 | Helped |
| Remove the entire perturbation scheme (ablation) | SESS · SUN RGB-D val, 10% labeled | mAP@0.25 | Hurt |
| Remove the entire perturbation scheme (ablation) | SESS · ScanNetV2 val, 30% labeled | mAP@0.25 | Hurt |
| Add random rotation perturbation (ablation) | SESS · SUN RGB-D val, 10% labeled | mAP@0.25 | Helped |
| Add random rotation perturbation (ablation) | SESS · ScanNetV2 val, 30% labeled | mAP@0.25 | Helped |
Closest papers by meaning
- Seg2Box: 3D Object Detection by Point-Wise Semantics Supervision (AAAI 2025 · similarity 0.89)
- Semi-supervised 3D Object Detection with PatchTeacher and PillarMix (AAAI 2024 · similarity 0.88)
- Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.88)
- Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection (CVPR 2025 · similarity 0.88)
- A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection (CVPR 2024 · similarity 0.88)
- SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts (CVPR 2025 · 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.