AI Paper Atlas

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

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
add adaptive resolution zoom-in to SEEM pseudo-labels (ablation)SEEM · UCF-QNRFMAE: 526.4 -> 391.2Improved
add adaptive resolution zoom-in to SEEM pseudo-labels (ablation)SEEM · ShanghaiTech AMAE: 394.2 -> 342.9Improved
add iterative point-prompted mask generation on top of AdaSEEM (ablation)AdaSEEM · ShanghaiTech AMAE: 342.9 -> 323.4Improved
train a new counting network on refined masks (Iter. 1 vs Iter. 0) (ablation)unsupervised counter · UCF-QNRFMAE: 195.9 -> 181.2Improved
add a second pseudo-label iteration (Iter. 2 vs Iter. 1) (ablation)unsupervised counter · UCF-QNRFMAE: 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-labelscounting errorImproved
use proposed unsupervised method instead of CrowdCLIPunsupervised crowd counting · ShanghaiTech BMAE: 69.3 -> 33.3Improved
run an additional iteration of pseudo-labels for localization (ablation)unsupervised localization · UCF-QNRFrecall: 0.101 -> 0.263Improved
run an additional iteration of pseudo-labels for localization (ablation)unsupervised localization · UCF-QNRFprecision: 0.777 -> 0.677Hurt
unsupervised counter versus supervised methods on dense dataOurs (Iter. 2) · ShanghaiTech AMAE: 102.6 vs MCNN 110.2, STEERER 54.5No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy