Research map / Detection and segmentation / Weakly supervised detection and segmentation
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation
Zelin Peng, Guanchun Wang, Lingxi Xie, Dongsheng Jiang, Wei Shen, Qi Tian
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 activation shape controlling (temperature) to CAM seed area (ablation) | USAGE · PASCAL VOC train seed (Transformer) | mIoU: 52.3 -> 64.0 | Improved |
| add activation shape controlling (temperature) to CAM seed area (ablation) | USAGE · PASCAL VOC train seed (CNN) | mIoU: 47.8 -> 49.6 | Improved |
| add activation shape regularization (network adjustment consistency) (ablation) | USAGE · PASCAL VOC train seed (CNN) | mIoU: 49.6 -> 57.7 | Improved |
| add activation shape regularization (ablation) | USAGE · PASCAL VOC train seed (Transformer) | mIoU: 64.0 -> 67.7 | Improved |
| use sharpening (small tau1) for Transformers instead of smoothing (large tau1) (ablation) | USAGE · PASCAL VOC train seed (Transformer) | mIoU: 50.3 -> 67.7 | Improved |
| use smoothing (large tau1=50) for CNNs instead of sharpening (ablation) | USAGE · PASCAL VOC train seed (CNN) | mIoU: 48.9 -> 57.7 | Improved |
| vary temperature tau1 within the correct regime (ablation) | USAGE · PASCAL VOC train seed | mIoU: 67.2 -> 67.7 -> 67.1 | No clear effect |
| replace network adjustment with geometric transform regularization (ablation) | USAGE (Transformer) · PASCAL VOC train seed | mIoU: 67.7 -> 62.4 | Hurt |
| replace network adjustment with online attention accumulation (ablation) | USAGE (Transformer) · PASCAL VOC train seed | mIoU: 67.7 -> 65.1 | Hurt |
| use self-adaptive adjustment gap instead of fixed gap (ablation) | USAGE (Transformer) · PASCAL VOC train seed | mIoU: 66.6 -> 67.7 | Improved |
| use self-adaptive adjustment gap instead of fixed gap (ablation) | USAGE (CNN) · PASCAL VOC train seed | mIoU: 55.5 -> 57.7 | Improved |
| add architecture adjustment regularization to CAM mapping (ablation) | CAM (Transformer) · PASCAL VOC train seed | mIoU: 52.3 -> 56.5 | Improved |
Later papers that compared with this method
5 later accepted papers report USAGE as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation (ECCV 2024 · better on 5 of 5 shared results)
- Diffusion-Guided Weakly Supervised Semantic Segmentation (ECCV 2024 · better on 4 of 4 shared results)
- Competing for Pixels: A Self-Play Algorithm for Weakly-Supervised Semantic Segmentation (TPAMI 2024 · better on 3 of 3 shared results)
- Class Tokens Infusion for Weakly Supervised Semantic Segmentation (CVPR 2024 · better on 2 of 2 shared results)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 2024 · better on 1 of 1 shared result)
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.
- CLIMS — CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation (CVPR 2022) · better on 1 of 1 shared result
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
- Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation (ECCV 2020 · similarity 0.90)
- Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing (CVPR 2018 · similarity 0.88)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · similarity 0.86)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.85)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.85)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.85)
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.
