Research map / Detection and segmentation / Weakly supervised detection and segmentation
Bias-Resilient Weakly Supervised Semantic Segmentation Using Normalizing Flows
Xianglin Qiu, Xiaoyang Wang, Zhen Zhang, Jimin Xiao
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 BRNF (normalizing-flow GMM calibration, feature sampling, denoising) to CLIP-ES | CLIP-ES · PASCAL VOC 2012 train (seed CAM) | mIoU: 70.8 -> 72.1 | Improved |
| add BRNF to CLIP-ES | CLIP-ES · PASCAL VOC 2012 train (pseudo-label mask) | mIoU: 75.0 -> 79.2 | Improved |
| add BRNF to SFC | SFC · PASCAL VOC 2012 train (seed CAM) | mIoU: 64.7 -> 70.7 | Improved |
| add BRNF to SFC | SFC · PASCAL VOC 2012 train (pseudo-label mask) | mIoU: 73.7 -> 77.4 | Improved |
| add BRNF to CLIP-ES then train DeepLabV2 | CLIP-ES · PASCAL VOC 2012 val | mIoU: 71.1 -> 75.9 | Improved |
| add BRNF to CLIP-ES then train DeepLabV2 | CLIP-ES · PASCAL VOC 2012 test | mIoU: 71.4 -> 76.2 | Improved |
| add BRNF to CLIP-ES then train DeepLabV2 | CLIP-ES · MS COCO 2014 val | mIoU: 45.4 -> 47.9 | Improved |
| add BRNF to SFC then train DeepLabV2 | SFC · PASCAL VOC 2012 val | mIoU: 71.2 -> 74.8 | Improved |
| add BRNF to SFC then train DeepLabV2 | SFC · MS COCO 2014 val | mIoU: 46.8 -> 47.7 | Improved |
| use CLIP-ES + BRNF instead of PSDPM guidance | PSDPM · PASCAL VOC 2012 val | mIoU: 74.1 -> 75.9 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MCTformer — MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation (TPAMI 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds (CVPR 2022 · similarity 0.89)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · similarity 0.88)
- DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.88)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.87)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.87)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 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.
