Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
Read the paperCheck 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 |
|---|---|---|---|
| Use MCOF with ResNet101 instead of the strongest reported baseline AE-PSL | PASCAL VOC 2012 val · PASCAL VOC 2012 val | mIoU: 55.0 -> 60.3 | Helped |
| Use MCOF with ResNet101 instead of the strongest reported baseline AE-PSL | PASCAL VOC 2012 test · PASCAL VOC 2012 test | mIoU: 55.7 -> 61.2 | Helped |
| Add RegionNet common-feature mining to initial object seeds (ablation) | MCOF · PASCAL VOC 2012 train | mIoU: 14.27 -> 29.1 | Helped |
| Add saliency-guided refinement after RegionNet (ablation) | MCOF · PASCAL VOC 2012 train | mIoU: 29.1 -> 34.8 | Helped |
| Train PixelNet on refined object regions (ablation) | MCOF iter1 · PASCAL VOC 2012 train | mIoU: 34.8 -> 48.4 | Helped |
| Continue progressive common-feature mining and network training (ablation) | MCOF, iterations 1 to 5 · PASCAL VOC 2012 val | mIoU: 44.4 -> 56.2 | Helped |
| Add saliency-guided refinement instead of omitting it (ablation) | MCOF PixelNet iter1 · PASCAL VOC 2012 val | mIoU: 41.8 -> 44.4 | Helped |
| Add saliency-guided refinement instead of omitting it (ablation) | MCOF PixelNet iter2 · PASCAL VOC 2012 val | mIoU: 46.2 -> 51.6 | Helped |
| Add saliency-guided refinement instead of omitting it (ablation) | MCOF PixelNet iter3 · PASCAL VOC 2012 val | mIoU: 47.7 -> 53.3 | Helped |
| Add saliency-guided refinement instead of omitting it (ablation) | MCOF PixelNet iter4 · PASCAL VOC 2012 val | mIoU: 51.5 -> 55.5 | Helped |
| Add saliency-guided refinement instead of omitting it (ablation) | MCOF PixelNet iter5 · PASCAL VOC 2012 val | mIoU: 52.1 -> 56.2 | Helped |
| Use iterative common-feature mining rather than direct iterative segmentation training (ablation) | MCOF · PASCAL VOC 2012 | mIoU | Helped |
Closest papers by meaning
- Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation (CVPR 2021 · similarity 0.92)
- Weakly-Supervised Semantic Segmentation via Sub-Category Exploration (CVPR 2020 · similarity 0.91)
- Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation (CVPR 2018 · similarity 0.91)
- Webly Supervised Semantic Segmentation (CVPR 2017 · similarity 0.91)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.91)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.90)
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.