Research map / Detection and segmentation / Weakly supervised detection and segmentation
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
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 MCG proposal refinement to BBAM masks (ablation) | BBAM instance segmentation · PASCAL VOC val | AP: 29.6 -> 33.4 | Helped |
| Add MCG proposal refinement to BBAM masks (ablation) | BBAM instance segmentation · MS COCO val | AP: 23.5 -> 26.0 | Helped |
| Use separate foreground and background thresholds, ignoring uncertain pixels, instead of assigning every pixel (ablation) | BBAM instance segmentation · PASCAL VOC val | AP: 24.8 -> 28.6 | Helped |
| Add seed growing for ignored pixels (ablation) | BBAM instance segmentation · PASCAL VOC val | AP: 28.6 -> 29.6 | Helped |
| Use both box-head and classification-head attribution maps rather than either head alone (ablation) | BBAM segmentation · PASCAL VOC | segmentation performance | Helped |
| Use an adaptive stride based on predicted box area instead of a fixed stride (ablation) | BBAM localization · PASCAL VOC val, objects of varied sizes | IoU | Helped |
| Set sparsity weight λ to 0.007 rather than 0.001 (ablation) | BBAM instance segmentation · PASCAL VOC val | AP: 26.6 -> 29.6 | Helped |
| Set sparsity weight λ to 0.007 rather than 0.001 (ablation) | BBAM semantic segmentation · PASCAL VOC val | mIoU: 67.9 -> 71.4 | Helped |
Closest papers by meaning
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation (CVPR 2017 · similarity 0.91)
- Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation (CVPR 2019 · similarity 0.89)
- Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior (NeurIPS 2019 · similarity 0.89)
- Sketchy Bounding-box Supervision for 3D Instance Segmentation (CVPR 2025 · similarity 0.87)
- Extreme Point Supervised Instance Segmentation (CVPR 2024 · similarity 0.87)
- WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels (CVPR 2025 · similarity 0.86)
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.