Research map / Detection and segmentation / Weakly supervised detection and segmentation
Non-Salient Region Object Mining for Weakly Supervised Semantic 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 graph-based global reasoning (GR) (ablation) | Weakly supervised segmentation with ResNet-101 · PASCAL VOC 2012 val | mIoU: 67.7 -> 68.8 | Helped |
| Add potential object mining (POM) to GR (ablation) | Weakly supervised segmentation with ResNet-101 · PASCAL VOC 2012 val | mIoU: 68.8 -> 69.0 | Helped |
| Retrain the segmentation network using its predictions without POM (ablation) | GR weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 68.8 -> 68.7 | Hurt |
| Add segmentation-network retraining with POM (ablation) | GR + POM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 69.0 -> 69.7 | Helped |
| Add non-salient region masking (NSRM) (ablation) | GR + POM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 69.7 -> 70.4 | Helped |
| Apply NSRM to all images rather than separating simple and complex images (ablation) | NSRM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 70.4 -> 68.8 | Hurt |
| Add object expansion within the salient region (ablation) | NSRM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 70.2 -> 70.4 | Helped |
| Add masking of the non-salient pseudo-label region (ablation) | NSRM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 70.0 -> 70.4 | Helped |
| Add dilation to the object mask (ablation) | NSRM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU: 68.5 -> 70.4 | Helped |
| Vary the NSRM dilation kernel size; sizes between 5 and 30 perform better than sizes that are too large or small (ablation) | NSRM weakly supervised segmentation · PASCAL VOC 2012 val | mIoU | Mixed |
| Vary the number of global-reasoning interaction nodes; a too-large number may not improve performance much (ablation) | Graph-based global reasoning unit · PASCAL VOC 2012 val | mIoU | No clear effect |
Closest papers by meaning
- Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (CVPR 2018 · similarity 0.92)
- Railroad Is Not a Train: Saliency As Pseudo-Pixel Supervision for Weakly Supervised Semantic Segmentation (CVPR 2021 · similarity 0.89)
- Weakly-Supervised Semantic Segmentation via Sub-Category Exploration (CVPR 2020 · similarity 0.89)
- Exploiting Saliency for Object Segmentation From Image Level Labels (CVPR 2017 · similarity 0.89)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.88)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 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.