Research map / Detection and segmentation / Open-set and few-shot detection
Robust Instance Segmentation Through Reasoning About Multi-Object Occlusion
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 |
|---|---|---|---|
| add multi-object occlusion reasoning to CompNet | CompNet · KINS modal | mIoU: 64.3 -> 67.2 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · KINS amodal | mIoU: 76.2 -> 76.7 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · Occlusion Challenge: 2 objects, modal | mIoU: 66.9 -> 73.1 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · Occlusion Challenge: 4 objects, modal | mIoU: 56.0 -> 65.0 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · Occlusion Challenge: 2 objects + unknown occlusion, modal | mIoU: 63.6 -> 65.8 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · Occlusion Challenge: 2 objects, amodal | mIoU: 76.7 -> 79.7 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · Occlusion Challenge: 4 objects, amodal | mIoU: 74.8 -> 79.5 | Helped |
| add multi-object occlusion reasoning to CompNet | CompNet · Occlusion Challenge: 2 objects + unknown occlusion, amodal | mIoU: 76.5 -> 76.6 | No clear effect |
| add pair-wise order recovery (ablation) | Occlusion reasoning module · Occlusion Challenge: 2 objects, modal | mIoU: 70.5 -> 73.1 | Helped |
| add pair-wise order recovery (ablation) | Occlusion reasoning module · Occlusion Challenge: 2 objects, amodal | mIoU: 77.8 -> 79.7 | Helped |
| add pair-wise order recovery (ablation) | Occlusion reasoning module · Occlusion Challenge: 4 objects, modal | mIoU: 58.5 -> 65.3 | Helped |
| add pair-wise order recovery (ablation) | Occlusion reasoning module · Occlusion Challenge: 4 objects, amodal | mIoU: 75.2 -> 79.5 | Helped |
Closest papers by meaning
- Deep Occlusion-Aware Instance Segmentation With Overlapping BiLayers (CVPR 2021 · similarity 0.91)
- In the Shadows, Shape Priors Shine: Using Occlusion to Improve Multi-Region Segmentation (CVPR 2016 · similarity 0.90)
- Learning Instance Occlusion for Panoptic Segmentation (CVPR 2020 · similarity 0.89)
- Robust Object Detection Under Occlusion With Context-Aware CompositionalNets (CVPR 2020 · similarity 0.88)
- Deep Supervision With Shape Concepts for Occlusion-Aware 3D Object Parsing (CVPR 2017 · similarity 0.88)
- unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning (ICML 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.