Research map / Detection and segmentation / Weakly supervised detection and segmentation
[Re] Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
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 BAP instead of GAP for classification and pseudo-label generation (ablation) | WSSS pseudo-label generator · PASCAL VOC 2012 val pseudo labels | mIoU: 76.1 -> 79.2 | Helped |
| add the background attention unary u_0 instead of using the background CAM (ablation) | BAP pseudo-label generator · PASCAL VOC 2012 val pseudo labels | mIoU: 77.8 -> 79.2 | Helped |
| use retrieval labels Y_ret in addition to DenseCRF labels Y_crf (ablation) | BAP pseudo-label generator · PASCAL VOC 2012 val pseudo labels | mIoU: 79.2 -> 69.9 | Hurt |
| add NAL for regions where the two pseudo labels disagree (ablation) | DeepLab-V1 · PASCAL VOC 2012 val, regions with disagreeing pseudo labels | mIoU: 61.8 / 67.5 -> 62.4 / 68.1 | Helped |
| use entropy regularization on regions with disagreeing pseudo labels (ablation) | DeepLab-V1 · PASCAL VOC 2012 val, regions with disagreeing pseudo labels | mIoU: 61.8 / 67.5 -> 61.4 / 67.3 | Hurt |
| use bootstrapping on regions with disagreeing pseudo labels (ablation) | DeepLab-V1 · PASCAL VOC 2012 val, regions with disagreeing pseudo labels | mIoU: 61.8 / 67.5 -> 61.9 / 67.6 | Helped |
| train the pseudo-label generator on COCO instead of transferring from VOC (ablation) | BAP instance pseudo-label generator · MS-COCO train pseudo labels | AP: 16.9 -> 22.2 | Helped |
Closest papers by meaning
- Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation (CVPR 2021 · similarity 0.92)
- POT: Prototypical Optimal Transport for Weakly Supervised Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.88)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.85)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.85)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.84)
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.