Research map / Label-efficient and robust learning / Recognition and long-tail
Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 depth, segmentation, and count auxiliary tasks (ablation) | CSRNet · ShanghaiTech-B | MAE: 10.6 -> 8.11 | Helped |
| add depth, segmentation, and count auxiliary tasks (ablation) | CSRNet · ShanghaiTech-B | MSE: 16.0 -> 13.53 | Helped |
| add depth, segmentation, and count auxiliary tasks | CSRNet · WorldExpo’2010 | Average MAE: 8.6 -> 7.8 | Helped |
| add depth, segmentation, and count auxiliary tasks | CFCN · Mall | MAE: 1.52 -> 2.28 | Hurt |
| add depth prediction auxiliary task (ablation) | CFCN · ShanghaiTech-B | MAE: 12.89 -> 11.72 | Helped |
| add crowd segmentation auxiliary task (ablation) | CFCN · ShanghaiTech-B | MAE: 12.89 -> 12.31 | Helped |
| add count regression auxiliary task (ablation) | CFCN · ShanghaiTech-B | MAE: 12.89 -> 12.24 | Helped |
| add depth, segmentation, and count auxiliary tasks (ablation) | CFCN · ShanghaiTech-B | MAE: 12.89 -> 11.05 | Helped |
| add depth prediction auxiliary task (ablation) | CFCN · Mall | MAE: 3.14 -> 2.79 | Helped |
| add crowd segmentation auxiliary task (ablation) | CFCN · Mall | MAE: 3.14 -> 2.68 | Helped |
| add count regression auxiliary task (ablation) | CFCN · Mall | MAE: 3.14 -> 2.83 | Helped |
| add depth, segmentation, and count auxiliary tasks (ablation) | CFCN · Mall | MAE: 3.14 -> 2.28 | Helped |
Closest papers by meaning
- Residual Regression With Semantic Prior for Crowd Counting (CVPR 2019 · similarity 0.89)
- Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (CVPR 2018 · similarity 0.89)
- Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (CVPR 2019 · similarity 0.89)
- Almost Unsupervised Learning for Dense Crowd Counting (AAAI 2019 · similarity 0.89)
- Free Lunch Enhancements for Multi-modal Crowd Counting (CVPR 2025 · similarity 0.87)
- Gramformer: Learning Crowd Counting via Graph-Modulated Transformer (AAAI 2024 · similarity 0.87)
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.