Research map / Detection and segmentation / CNN features
Proposal-Free Network for Instance-Level Object Segmentation
Xiaodan Liang, Liang Lin, Yunchao Wei, Xiaohui Shen, Jianchao Yang, Shuicheng Yan
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 |
|---|---|---|---|
| use two-stage training instead of one unified network (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 49.1 -> 58.7 | Improved |
| predict 6-d box coordinates instead of 2-d offsets (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 51.0 -> 58.7 | Improved |
| predict 6-d location instead of centers only (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 57.1 -> 58.7 | Improved |
| add 4 more corner coordinates (10-d) to the 6-d location | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 58.7 -> 59.0 | No clear effect |
| add multi-scale prediction streams (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 55.2 -> 58.7 | Improved |
| add spatial coordinate maps to the location branch (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 58.0 -> 58.7 | Improved |
| concatenate with 1x1 conv fusion instead of element-wise sum (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 58.3 -> 58.7 | Improved |
| add category-level features to instance number prediction (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 51.4 -> 58.7 | Improved |
| add instance-level features to instance number prediction (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 57.9 -> 58.7 | Improved |
| train instance location and number jointly instead of separately (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 58.1 -> 58.7 | Improved |
| add spatial coordinates to the clustering similarity (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 55.3 -> 58.7 | Improved |
| add instance-number category refinement (ablation) | PFN · PASCAL VOC 2012 val | AP^r at IoU 0.5 (%): 57.4 -> 58.7 | Improved |
Closest papers by meaning
- Pixelwise Instance Segmentation With a Dynamically Instantiated Network (CVPR 2017 · similarity 0.89)
- P2Object: Single Point Supervised Object Detection and Instance Segmentation (IJCV 2025 · similarity 0.89)
- Boundary-Aware Instance Segmentation (CVPR 2017 · similarity 0.89)
- Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation (TPAMI 2020 · similarity 0.89)
- 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation (CVPR 2020 · similarity 0.88)
- Semantic-aware SAM for Point-Prompted Instance Segmentation (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.
