Research map / Detection and segmentation / CNN features
Joint Training of Cascaded CNN for Face Detection
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 |
|---|---|---|---|
| Jointly train the cascaded CNN stages instead of training them separately (ablation) | FaceCraft · FDDB (1000 false positives) | recall: 87.2% -> 88.2% | Helped |
| Train with the enlarged 3R+ dataset (ablation) | FaceCraft · AFW | AP: 98.22% -> 98.73% | Helped |
| Train with the enlarged 3R+ dataset (ablation) | FaceCraft · FDDB (1000 false positives) | recall: 88.2% -> 90.8% | Helped |
| Jointly fine-tune RPN and Fast R-CNN rather than use the four-stage separate training procedure (ablation) | RPN + Fast R-CNN · AFW | AP: 97.0% -> 98.7% | Helped |
| Jointly fine-tune RPN and Fast R-CNN rather than use the four-stage separate training procedure (ablation) | RPN + Fast R-CNN · FDDB (1000 false positives) | recall: 89.7% -> 91.2% | Helped |
| Use the fast testing version with its efficiency optimizations (ablation) | FaceCraft · FDDB (1000 false positives) | recall: 88.2% -> 87.3% | Hurt |
Closest papers by meaning
- Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018 · similarity 0.87)
- Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution (NeurIPS 2019 · similarity 0.86)
- Mnemonic Descent Method: A Recurrent Process Applied for End-To-End Face Alignment (CVPR 2016 · similarity 0.86)
- Weakly Supervised Cascaded Convolutional Networks (CVPR 2017 · similarity 0.86)
- Hybrid Task Cascade for Instance Segmentation (CVPR 2019 · similarity 0.85)
- Bi-Directional Cascade Network for Perceptual Edge Detection (CVPR 2019 · similarity 0.84)
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.