Research map / Detection and segmentation / Weakly supervised detection and segmentation
Complementary Patch for Weakly Supervised Semantic Segmentation
Fei Zhang, Chaochen Gu, Chenyue Zhang, Yuchao Dai
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 L_tcp and PCM (ablation) | baseline CAM · VOC12 train pseudo-label mIoU | mIoU (%): 47.84 -> 51.08 | Improved |
| add CP cross regularization L_cpcr (ablation) | CPN · VOC12 train pseudo-label mIoU | mIoU (%): 51.08 -> 55.71 | Improved |
| apply online hard example mining to L_cpcr (ablation) | CPN · VOC12 train pseudo-label mIoU | mIoU (%): 55.71 -> 56.58 | Improved |
| add Pixel-Region Correlation Module (PRCM) (ablation) | CPN · VOC12 train pseudo-label mIoU | mIoU (%): 56.58 -> 57.43 | Improved |
| add PRCM to SEAM (multi-scale) (ablation) | SEAM · VOC12 train pseudo-label mIoU | mIoU (%): 55.41 -> 55.71 | Improved |
| use CPN instead of baseline CAM (multi-scale) | baseline CAM · VOC12 train pseudo-label mIoU | mIoU (%): 47.84 -> 57.43 | Improved |
| use CPN instead of SEAM at image scale 0.5 | SEAM · VOC12 train pseudo-label mIoU (scale 0.5) | mIoU (%): 49.35 -> 48.91 | Hurt |
| use CPN instead of SEAM (multi-scale) | SEAM · VOC12 train pseudo-label mIoU | mIoU (%): 55.41 -> 57.43 | Improved |
| increase super-pixel number from 200 to 8000 (smaller patches) (ablation) | CPN super-pixel patch · VOC12 train pseudo-label mIoU | mIoU (%): 57.43 -> 55.79 | Hurt |
| use grid patch set K={56,112} instead of K={4,7} (ablation) | CPN grid patch · VOC12 train pseudo-label mIoU | mIoU (%): 55.67 -> 57.07 | Improved |
| use grid patch set K={224,448} instead of K={56,112} (larger patches) (ablation) | CPN grid patch · VOC12 train pseudo-label mIoU | mIoU (%): 57.07 -> 55.80 | Hurt |
| raise hidden probability from 0.1 to 0.5 (ablation) | CPN · VOC12 train pseudo-label mIoU | mIoU (%): 55.52 -> 57.43 | Improved |
Closest papers by meaning
- Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation (CVPR 2023 · similarity 0.92)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.91)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.91)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.90)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.90)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · 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.
