Research map / Detection and segmentation / Weakly supervised detection and segmentation
A Weakly Supervised Amodal Segmenter With Boundary Uncertainty Estimation
Khoi Nguyen, Sinisa Todorovic
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 occlusion boundary input instead of occluder mask (ablation) | PCNet-m · COCOA-val | mIoU: 80.73 -> 82.85 | Improved |
| add occlusion boundary input instead of occluder mask (ablation) | PCNet-m · COCOA-val | O-Acc: 85.75 -> 89.01 | Improved |
| add occlusion boundary input instead of occluder mask (ablation) | PCNet-m · KINS-test | inv-mIoU: 59.24 -> 62.77 | Improved |
| add uncertainty-weighted loss (ablation) | PCNet-m · COCOA-val | mIoU: 80.73 -> 82.49 | Improved |
| add uncertainty-weighted loss (ablation) | PCNet-m · COCOA-test | O-Acc: 86.73 -> 88.40 | Improved |
| add uncertainty-weighted loss (ablation) | PCNet-m · KINS-test | inv-mIoU: 59.24 -> 62.00 | Improved |
| use proposed uncertainty data term rather than uncertainty-weighted BCE (ablation) | ASBU · COCOA-val | mIoU: 83.18 -> 84.22 | Improved |
| use proposed uncertainty data term rather than uncertainty-weighted BCE (ablation) | ASBU · KINS-test | mIoU: 94.34 -> 94.83 | Improved |
| combine boundary input and uncertainty loss (full ASBU) | PCNet-m · COCOA-test | mIoU: 86.63 -> 89.87 | Improved |
| combine boundary input and uncertainty loss (full ASBU) | PCNet-m · KINS-test | mIoU: 94.52 -> 94.83 | No clear effect |
| train Mask-RCNN on ASBU pseudo masks instead of PCNet-m pseudo masks | Mask-RCNN · COCOA-test | AP: 22.6 -> 23.8 | Improved |
| train Mask-RCNN on ASBU pseudo masks instead of PCNet-m pseudo masks | Mask-RCNN · KINS-test | AP: 29.1 -> 29.3 | No clear effect |
Closest papers by meaning
- Amodal Ground Truth and Completion in the Wild (CVPR 2024 · similarity 0.91)
- BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion (AAAI 2024 · similarity 0.90)
- Using Diffusion Priors for Video Amodal Segmentation (CVPR 2025 · similarity 0.90)
- Towards Efficient Foundation Model for Zero-shot Amodal Segmentation (CVPR 2025 · similarity 0.89)
- Segment Anything, Even Occluded (CVPR 2025 · similarity 0.89)
- pix2gestalt: Amodal Segmentation by Synthesizing Wholes (CVPR 2024 · similarity 0.88)
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.
