Research map / Label-efficient and robust learning / Semi-supervised learning
Spatial Uncertainty-Aware Semi-Supervised Crowd Counting
Yanda Meng, Hongrun Zhang, Yitian Zhao, Xiaoyun Yang, Xuesheng Qian, Xiaowei Huang, Yalin Zheng
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 both hard and soft uncertainty maps (ablation) | Mean-Teacher crowd counting · SHA | MAE: 81.1 -> 68.5 | Improved |
| add both hard and soft uncertainty maps (ablation) | Mean-Teacher crowd counting · SHA | RMSE: 143.1 -> 121.9 | Improved |
| add both hard and soft uncertainty maps (ablation) | Mean-Teacher crowd counting · JHU-Crowd | MAE: 96.1 -> 80.7 | Improved |
| add both hard and soft uncertainty maps (ablation) | Mean-Teacher crowd counting · JHU-Crowd | RMSE: 311.9 -> 290.8 | Improved |
| add hard uncertainty map only (ablation) | Mean-Teacher crowd counting · SHA | MAE: 81.1 -> 77.3 | Improved |
| add soft uncertainty map only (ablation) | Mean-Teacher crowd counting · SHA | MAE: 81.1 -> 73.1 | Improved |
| add soft uncertainty map only (ablation) | Mean-Teacher crowd counting · JHU-Crowd | MAE: 96.1 -> 85.3 | Improved |
| use soft rather than hard uncertainty map (ablation) | Mean-Teacher crowd counting · SHA | MAE: 77.3 -> 73.1 | Improved |
| use hard plus soft instead of two hard maps (ablation) | uncertainty-aware crowd counting · SHA | MAE: 72.1 -> 68.5 | Improved |
| use hard plus soft instead of two soft maps (ablation) | uncertainty-aware crowd counting · SHA | MAE: 70.5 -> 68.5 | Improved |
| use hard plus soft instead of two hard maps (ablation) | uncertainty-aware crowd counting · JHU-Crowd | MAE: 83.2 -> 80.7 | Improved |
| add unlabeled data with the full semi-supervised framework (vs label-only) | Ours · SHA | MAE: 94.6 -> 68.5 | Improved |
Closest papers by meaning
- Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks (ECCV 2020 · similarity 0.93)
- Calibrating Uncertainty for Semi-Supervised Crowd Counting (ICCV 2023 · similarity 0.92)
- Reducing Spatial Labeling Redundancy for Active Semi-Supervised Crowd Counting (TPAMI 2022 · similarity 0.91)
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting (NeurIPS 2026 · similarity 0.89)
- Semi-Supervised Counting via Pixel-by-Pixel Density Distribution Modeling (TPAMI 2025 · similarity 0.89)
- Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting (CVPR 2025 · similarity 0.88)
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.
