Research map / Architectures and efficiency / CNN design
Crowd Counting With Deep Negative Correlation Learning
Zenglin Shi, Le Zhang, Yun Liu, Xiaofeng Cao, Yangdong Ye, Ming-Ming Cheng, Guoyan Zheng
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 negative-correlation regularization to the conventional ensemble (ablation) | D-ConvNet-v1 · UCF CC 50 | MAE: 380.5 -> 288.4 | Improved |
| Add negative-correlation regularization to the conventional ensemble (ablation) | D-ConvNet-v1 · UCF CC 50 | RMSE: 527.2 -> 404.7 | Improved |
| Add negative-correlation regularization to the conventional ensemble (ablation) | D-ConvNet-v1 · ShanghaiTech Part A | MAE: 91.6 -> 73.5 | Improved |
| Add negative-correlation regularization to the conventional ensemble (ablation) | D-ConvNet-v1 · ShanghaiTech Part B | MAE: 21.3 -> 18.7 | Improved |
| Add negative-correlation regularization to the conventional ensemble (ablation) | D-ConvNet-v1 · WorldExpo'10 | MAE: 16.4 -> 9.1 | Improved |
| Use the customized shallower network instead of VGG16 (ablation) | D-ConvNet · UCF CC 50 | MAE: 288.4 -> 354.1 | Hurt |
| Use the customized shallower network instead of VGG16 (ablation) | D-ConvNet · ShanghaiTech Part A | MAE: 73.5 -> 101.7 | Hurt |
| Use the customized shallower network instead of VGG16 (ablation) | D-ConvNet · ShanghaiTech Part B | MAE: 18.7 -> 25.7 | Hurt |
| Use the customized shallower network instead of VGG16 (ablation) | D-ConvNet · WorldExpo'10 average | MAE: 9.1 -> 10.7 | Hurt |
| Set NCL correlation coefficient λ to a relatively smaller value in [10−3, 10−2] (ablation) | D-ConvNet · Crowd counting datasets | MAE | No clear effect |
| Increase ensemble size beyond 64 regressors (ablation) | D-ConvNet · Crowd counting datasets | MAE | No clear effect |
Closest papers by meaning
- Switching Convolutional Neural Network for Crowd Counting (CVPR 2017 · similarity 0.88)
- Spatiotemporal Modeling for Crowd Counting in Videos (ICCV 2017 · similarity 0.88)
- Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (CVPR 2019 · similarity 0.88)
- Residual Regression With Semantic Prior for Crowd Counting (CVPR 2019 · similarity 0.88)
- Context-Aware Crowd Counting (CVPR 2019 · similarity 0.88)
- Shallow Feature Based Dense Attention Network for Crowd Counting (AAAI 2020 · 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.
