Research map / Architectures and efficiency / CNN design
Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
Xiyang Liu, Jie Yang, Wenrui Ding, Tieqiang Wang, Zhijin Wang, Junjun Xiong
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 |
|---|---|---|---|
| regress local counting map instead of density map (ablation) | VGG16 · ShanghaiTech Part A | MAE: 72.98 -> 69.52 | Improved |
| regress local counting map instead of density map (ablation) | VGG16 · ShanghaiTech Part B | MAE: 9.79 -> 8.96 | Improved |
| regress local counting map instead of density map (ablation) | VGG16 · ShanghaiTech Part A | MSE: 114.89 -> 110.23 | Improved |
| add mixture regression module (MRM) to LCM baseline (ablation) | VGG16+LCM · ShanghaiTech Part A | MAE: 69.52 -> 65.24 | Improved |
| add mixture regression module (MRM) to LCM baseline (ablation) | VGG16+LCM · ShanghaiTech Part B | MAE: 8.96 -> 7.79 | Improved |
| add adaptive soft interval module (ASIM) (ablation) | MRM · ShanghaiTech Part A | MAE: 65.24 -> 63.85 | Improved |
| add adaptive soft interval module (ASIM) (ablation) | MRM · ShanghaiTech Part B | MAE: 7.79 -> 7.56 | Improved |
| add scale-aware module (SAM) (ablation) | MRM+ASIM · ShanghaiTech Part A | MAE: 63.85 -> 61.59 | Improved |
| add scale-aware module (SAM) (ablation) | MRM+ASIM · ShanghaiTech Part B | MAE: 7.56 -> 7.02 | Improved |
| use 64x64 local patch instead of 16x16 (ablation) | MRM · ShanghaiTech Part A | MAE: 70.45 -> 65.24 | Improved |
| use 64x64 local patch instead of 128x128 (ablation) | MRM · ShanghaiTech Part A | MAE: 67.73 -> 65.24 | Improved |
| use 64x64 local patch instead of 128x128 (ablation) | MRM · ShanghaiTech Part B | MAE: 7.93 -> 7.79 | Improved |
Closest papers by meaning
- AutoScale: Learning to Scale for Crowd Counting (IJCV 2022 · similarity 0.91)
- Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization (CVPR 2019 · similarity 0.90)
- Adapting Lightweight Image-based Counting Models for Video Crowd Counting (CVPR 2026 · similarity 0.90)
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting (NeurIPS 2026 · similarity 0.90)
- To Choose or to Fuse? Scale Selection for Crowd Counting (AAAI 2021 · similarity 0.90)
- Single Domain Generalization for Crowd Counting (CVPR 2024 · similarity 0.89)
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.
