Research map / Detection and segmentation / CNN features
MT-ORL: Multi-Task Occlusion Relationship Learning
Panhe Feng, Qi She, Lei Zhu, Jiaxin Li, Lin Zhang, Zijian Feng, Changhu Wang, Chunpeng Li, Xuejing Kang, Anlong Ming
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 |
|---|---|---|---|
| share top-2 stages rather than top-1 stage (ablation) | OPNet · PIOD | boundary AP: 80.8 -> 83.1 | Improved |
| share top-2 stages rather than top-3 stages (ablation) | OPNet · PIOD | boundary AP: 80.6 -> 83.1 | Improved |
| share top-2 stages rather than top-4 stages (ablation) | OPNet · PIOD | boundary AP: 79.7 -> 83.1 | Improved |
| add orthogonal occlusion representation (OOR) in place of dbr orientation loss (ablation) | OPNet · PIOD | orientation AP: 75.9 -> 79.4 | Improved |
| add OOR in place of dbr orientation loss (ablation) | OPNet · BSDS ownership | orientation AP: 50.5 -> 60.1 | Improved |
| add OOR in place of dor orientation loss (ablation) | OPNet · PIOD | orientation AP: 72.2 -> 79.4 | Improved |
| add OOR in place of dbr orientation loss (ablation) | OPNet · BSDS ownership | boundary AP: 62.4 -> 66.8 | Improved |
| use five-scale supervision rather than one side map (ablation) | OPNet boundary path · PIOD | boundary AP: 77.4 -> 83.1 | Improved |
| use five-scale supervision rather than four (ablation) | OPNet boundary path · PIOD | boundary AP: 81.1 -> 83.1 | Improved |
| use two-scale supervision rather than three (ablation) | OPNet boundary path · PIOD | boundary AP: 82.6 -> 82.0 | No clear effect |
| shared-high, separated-low OPNet architecture with dbr loss vs OFNet | OPNet + dbr · PIOD | boundary AP: 77.0 -> 80.6 | Improved |
| train joint branches instead of boundary branch only | OPNet · PIOD | boundary AP: 79.5 -> 83.1 | Improved |
Closest papers by meaning
- Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning (ICCV 2019 · similarity 0.92)
- DOC: Deep OCclusion Estimation from a Single Image (ECCV 2016 · similarity 0.89)
- Pixel-Pair Occlusion Relationship Map (P2ORM): Formulation, Inference & Application (ECCV 2020 · similarity 0.87)
- Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation (ECCV 2018 · similarity 0.86)
- Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion (AAAI 2024 · similarity 0.84)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 2025 · similarity 0.84)
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.
