Research map / Learning theory and algorithms / Prediction and decision losses
Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd Counting
Changan Wang, Qingyu Song, Boshen Zhang, Yabiao Wang, Ying Tai, Xuyi Hu, Chengjie Wang, Jilin Li, Jiayi Ma, Yang Wu
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 mean count proxies (MCP) (ablation) | UEPNet · SHTech Part A | MAE: 61.56 -> 58.69 | Improved |
| add mean count proxies (MCP) (ablation) | UEPNet · SHTech Part B | MAE: 7.72 -> 7.64 | Improved |
| add interleaved prediction heads (IPH) over MCP (ablation) | UEPNet · SHTech Part A | MAE: 58.69 -> 56.80 | Improved |
| add interleaved prediction heads (IPH) over MCP (ablation) | UEPNet · SHTech Part B | MAE: 7.64 -> 7.25 | Improved |
| use parallel heads with identical intervals (PPH) instead of IPH (ablation) | UEPNet · SHTech Part A | MAE: 58.69 -> 58.47 | No clear effect |
| use parallel heads with identical intervals (PPH) instead of IPH (ablation) | UEPNet · SHTech Part B | MAE: 7.64 -> 7.57 | No clear effect |
| add multi-scale training to MCP+IPH (ablation) | UEPNet · SHTech Part A | MAE: 56.80 -> 54.64 | Improved |
| add multi-scale training to MCP+IPH (ablation) | UEPNet · SHTech Part B | MAE: 7.25 -> 6.38 | Improved |
| divide intervals with UEP instead of UniformLen (median proxy) (ablation) | UEPNet · SHTech Part B | MAE: 82.62 -> 7.72 | Improved |
| divide intervals with UEP instead of UniformNum (median proxy) (ablation) | UEPNet · SHTech Part B | MAE: 62.46 -> 7.72 | Improved |
| use MCP instead of median count proxy with UEP intervals (ablation) | UEPNet · SHTech Part B discretization error | discretization error: 1.88 -> 0.27 | Improved |
| add multi-scale training to MSE regression (ablation) | MSE regression baseline · SHTech Part B | MAE: 13.57 -> 14.65 | Hurt |
Closest papers by meaning
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting (NeurIPS 2026 · similarity 0.88)
- Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting (CVPR 2019 · similarity 0.87)
- Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting (ECCV 2020 · similarity 0.87)
- Distribution Matching for Crowd Counting (NeurIPS 2020 · similarity 0.87)
- Learning to Count via Unbalanced Optimal Transport (AAAI 2021 · similarity 0.87)
- Free Lunch Enhancements for Multi-modal Crowd Counting (CVPR 2025 · similarity 0.86)
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.
