Research map / Detection and segmentation / Open-set and few-shot detection
3D Indoor Instance Segmentation in an Open-World
Mohamed El Amine Boudjoghra, Salwa K. Al Khatib, Jean Lahoud, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Khan
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 confidence thresholding (CT) to finetuned model (ablation) | 3D-OWIS · Split A Task 1 | WI: 1.589 -> 0.237 | Improved |
| Add confidence thresholding (CT) to finetuned model (ablation) | 3D-OWIS · Split B Task 1 | mAP (All): 18.70 -> 23.50 | Improved |
| Add confidence thresholding (CT) to finetuned model (ablation) | 3D-OWIS · Split C Task 1 | WI: 2.901 -> 0.227 | Improved |
| Add confidence thresholding (CT) to finetuned model (ablation) | 3D-OWIS · Split C Task 1 | U-Recall: 15.66 -> 11.44 | Hurt |
| Add probability correction (PC) on top of finetuning and CT (ablation) | 3D-OWIS · Split A Task 2 | U-Recall: 23.62 -> 27.03 | Improved |
| Add probability correction (PC) on top of finetuning and CT (ablation) | 3D-OWIS · Split B Task 2 | U-Recall: 20.90 -> 24.21 | Improved |
| Add probability correction (PC) on top of finetuning and CT (ablation) | 3D-OWIS · Split A Task 1 | WI: 0.237 -> 0.398 | Hurt |
| Add probability correction (PC) on top of finetuning and CT (ablation) | 3D-OWIS · Split B Task 1 | A-OSE: 1397 -> 1780 | Hurt |
| Add confidence thresholding with finetuning (vs finetuning alone) (ablation) | 3D-OWIS · Split A Task 2 | mAP (All): 14.10 -> 22.30 | Improved |
| Use exemplar replay with finetuning (ablation) | 3D-OWIS · Split A Task 2 | previously known mAP: 00.00 -> 11.00 | Improved |
| Replace 3D-OW-DETR with 3D-OWIS | Open-world 3D instance segmentation · Split A Task 1 | U-Recall: 22.14 -> 34.75 | Improved |
| Replace 3D-OW-DETR with 3D-OWIS | Open-world 3D instance segmentation · Split B Task 3 | mAP (All): 11.62 -> 20.90 | Improved |
Closest papers by meaning
- Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024 · similarity 0.91)
- UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes (CVPR 2024 · similarity 0.90)
- Segment Any 3D Object with Language (ICLR 2025 · similarity 0.89)
- Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation (ICLR 2025 · similarity 0.88)
- SAI3D: Segment Any Instance in 3D Scenes (CVPR 2024 · similarity 0.88)
- Open-World Semantic Segmentation Including Class Similarity (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.
