Research map / Detection and segmentation / Weakly supervised detection and segmentation
Robust Zero-Shot Crowd Counting and Localization with Adaptive Resolution SAM
Jia Wan, Qiangqiang Wu, Wei Lin, Antoni Chan
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 adaptive resolution zoom-in to SEEM pseudo-labels (ablation) | SEEM · UCF-QNRF | MAE: 526.4 -> 391.2 | Improved |
| add adaptive resolution zoom-in to SEEM pseudo-labels (ablation) | SEEM · ShanghaiTech A | MAE: 394.2 -> 342.9 | Improved |
| add iterative point-prompted mask generation on top of AdaSEEM (ablation) | AdaSEEM · ShanghaiTech A | MAE: 342.9 -> 323.4 | Improved |
| train a new counting network on refined masks (Iter. 1 vs Iter. 0) (ablation) | unsupervised counter · UCF-QNRF | MAE: 195.9 -> 181.2 | Improved |
| add a second pseudo-label iteration (Iter. 2 vs Iter. 1) (ablation) | unsupervised counter · UCF-QNRF | MAE: 181.2 -> 182.3 (MSE 304.7 -> 289.9) | Mixed |
| fit GMM to soft mask for head location instead of fixed head-height ratio (ablation) | robust localization · point pseudo-labels | counting error | Improved |
| use proposed unsupervised method instead of CrowdCLIP | unsupervised crowd counting · ShanghaiTech B | MAE: 69.3 -> 33.3 | Improved |
| run an additional iteration of pseudo-labels for localization (ablation) | unsupervised localization · UCF-QNRF | recall: 0.101 -> 0.263 | Improved |
| run an additional iteration of pseudo-labels for localization (ablation) | unsupervised localization · UCF-QNRF | precision: 0.777 -> 0.677 | Hurt |
| unsupervised counter versus supervised methods on dense data | Ours (Iter. 2) · ShanghaiTech A | MAE: 102.6 vs MCNN 110.2, STEERER 54.5 | No clear effect |
Closest papers by meaning
- Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework (ICCV 2021 · similarity 0.91)
- Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization (CVPR 2019 · similarity 0.90)
- AutoScale: Learning to Scale for Crowd Counting (IJCV 2022 · similarity 0.90)
- Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection (TPAMI 2020 · similarity 0.90)
- Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting (ECCV 2020 · 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.
