Research map / Detection and segmentation / CNN features
Discriminative Feature Transformation for Occluded Pedestrian Detection
Chunluan Zhou, Ming Yang, Junsong Yuan
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 attention module to Fast R-CNN | FRCN · Caltech Heavy | log-average miss rate: 44.3 -> 39.7 | Improved |
| add attention module to Fast R-CNN | FRCN · CityPersons Heavy | log-average miss rate: 49.2 -> 47.4 | Improved |
| add negative-only feature transformation (NT) (ablation) | FRCN+A · Caltech Reasonable | log-average miss rate: 8.8 -> 8.5 | No clear effect |
| add positive-only feature transformation (PT) (ablation) | FRCN+A · Caltech Partial | log-average miss rate: 15.1 -> 13.1 | Improved |
| add discriminative transformation (DT) (ablation) | FRCN+A · Caltech Reasonable | log-average miss rate: 8.8 -> 8.0 | Improved |
| add discriminative transformation (DT) (ablation) | FRCN+A · Caltech Partial | log-average miss rate: 15.1 -> 12.2 | Improved |
| add discriminative transformation (DT) (ablation) | FRCN+A · Caltech Heavy | log-average miss rate: 39.7 -> 37.9 | Improved |
| add feature transformation loss to transform branch (ablation) | FRCN+A+TB · Caltech Partial | log-average miss rate: 14.4 -> 12.2 | Improved |
| add discriminative transformation (DT) (ablation) | FRCN+A · CityPersons Heavy | log-average miss rate: 47.4 -> 44.3 | Improved |
| add transformation loss over transform branch alone (ablation) | FRCN+A+TB · CityPersons Heavy | log-average miss rate: 46.6 -> 44.3 | Improved |
| vary overlap thresholds tau1/tau2 for centroids (ablation) | FRCN+A+DT · Caltech | log-average miss rate: 8.0 +/- 0.4 / 12.2 +/- 0.6 / 37.9 +/- 0.5 | No clear effect |
| vary score thresholds s1/s2 for centroids (ablation) | FRCN+A+DT · Caltech | log-average miss rate: 8.0 +/- 0.5 / 12.2 +/- 0.7 / 37.9 +/- 0.5 | No clear effect |
Closest papers by meaning
- Mask-Guided Attention Network for Occluded Pedestrian Detection (ICCV 2019 · similarity 0.90)
- Bi-box Regression for Pedestrian Detection and Occlusion Estimation (ECCV 2018 · similarity 0.89)
- Occluded Pedestrian Detection Through Guided Attention in CNNs (CVPR 2018 · similarity 0.88)
- Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd (ECCV 2018 · similarity 0.88)
- High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection (CVPR 2019 · similarity 0.87)
- Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians (CVPR 2020 · 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.
