Research map / Detection and segmentation / Open-set and few-shot detection
Indoor Scene Parsing With Instance Segmentation, Semantic Labeling and Support Relationship Inference
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 |
|---|---|---|---|
| Jointly infer region selection and semantic labels instead of using region-only segmentation (ablation) | Indoor scene parsing on NYUv2 · NYUv2 | weighted coverage: 58.9 -> 59.3 | Helped |
| Add joint support relationship inference to region and semantic prediction (ablation) | Indoor scene parsing on NYUv2 · NYUv2 | support recall: 39.0 -> 43.1 | Helped |
| Add features linking support and semantics (ablation) | Ours-ND · NYUv2 | support recall: 41.9 -> 43.1 | Helped |
| Add features linking support and semantics (ablation) | Ours-ND · NYUv2 | support precision: 47.0 -> 47.6 | Helped |
| Use ground-truth semantics rather than predicted semantics (ablation) | Ours · NYUv2 | support recall: 43.1 -> 45.0 | Helped |
| Jointly infer region selection and semantic labels instead of using region-only segmentation (ablation) | Indoor scene parsing with RGBD on NYUv2 · NYUv2 RGBD | weighted coverage: 61.1 -> 62.8 | Helped |
| Jointly predict all three variable types rather than omit support inference (ablation) | Indoor scene parsing with RGBD on NYUv2 · NYUv2 RGBD | semantic average accuracy: 74.8 -> 75.3 | Helped |
| Jointly predict all three variable types rather than omit support inference (ablation) | Indoor scene parsing with RGBD on NYUv2 · NYUv2 RGBD | weighted coverage: 62.8 -> 62.7 | No clear effect |
Closest papers by meaning
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.88)
- Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball (CVPR 2024 · similarity 0.86)
- Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.86)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.86)
- Geometric Exploitation for Indoor Panoramic Semantic Segmentation (NeurIPS 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.