Research map / Detection and segmentation / 3D detection and driving
Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
Yun Zhu, Jianjun Qian, Jian Yang, Jin Xie, Na Zhao
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 unknown object mining (UOM) (ablation) | VLM-vanilla TR3D · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 14.09 -> 25.43 | Improved |
| add unknown object weighting (UOW) (ablation) | UOM model · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 25.43 -> 32.46 | Improved |
| add gated multimodal prototype imprinting (GPI) (ablation) | UOM + UOW · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 32.46 -> 38.48 | Improved |
| add GPI (ablation) | UOM only · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 25.43 -> 28.94 | Improved |
| add modality weights alpha (ablation) | GPI · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 32.46 -> 36.58 | Improved |
| add class re-balancing gamma (ablation) | GPI · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 32.46 -> 34.68 | Improved |
| add both alpha and gamma (ablation) | GPI · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 36.58 -> 38.48 | Improved |
| add box-level mining to feature-level mining (ablation) | UOM · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 3.53 -> 25.43 | Improved |
| add box-level weighting to point-level weighting (ablation) | UOW · ScanNet V2 1-way 5-shot | Novel mAP@0.25: 31.71 -> 38.48 | Improved |
| use GroundingDINO instead of YOLO-World (ablation) | FI3Det · ScanNet V2 9-way 5-shot | Novel mAP@0.25: 26.38 -> 30.23 | Improved |
| add FI3Det modules over VLM-vanilla | TR3D · ScanNet V2 1-way 1-shot | Novel mAP@0.25: 7.50 -> 35.58 | Improved |
| add FI3Det modules over VLM-vanilla | TR3D · SUN RGB-D 1-way 5-shot | Novel mAP@0.25: 11.93 -> 73.17 | Improved |
Closest papers by meaning
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.88)
- UniDet3D: Multi-dataset Indoor 3D Object Detection (AAAI 2025 · similarity 0.87)
- Towards 3D Objectness Learning in an Open World (NeurIPS 2025 · similarity 0.87)
- Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection (CVPR 2025 · similarity 0.87)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.86)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.86)
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.
