Research map / Detection and segmentation / CNN features
Illuminating Pedestrians via Simultaneous Detection & Segmentation
Garrick Brazil, Xi Yin, Xiaoming Liu
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 weak segmentation supervision (segmentation infusion layer) (ablation) | SDS-RCNN · Caltech reasonable | fused miss rate (%): 10.41 -> 7.36 | Improved |
| add weak segmentation supervision (ablation) | SDS-RCNN RPN · Caltech reasonable | RPN miss rate (%): 13.84 -> 10.67 | Improved |
| add weak segmentation supervision (ablation) | SDS-RCNN BCN · Caltech reasonable | BCN miss rate (%): 18.76 -> 10.98 | Improved |
| add 20% proposal padding (ablation) | SDS-RCNN · Caltech reasonable | fused miss rate (%): 7.69 -> 7.36 | Improved |
| add 20% proposal padding (ablation) | SDS-RCNN BCN · Caltech reasonable | BCN miss rate (%): 13.09 -> 10.98 | Improved |
| add cost-sensitive weighting (ablation) | SDS-RCNN RPN · Caltech reasonable | RPN miss rate (%): 9.63 -> 10.67 | Hurt |
| add cost-sensitive weighting (ablation) | SDS-RCNN BCN · Caltech reasonable | BCN miss rate (%): 14.87 -> 10.98 | Improved |
| add cost-sensitive weighting (ablation) | SDS-RCNN · Caltech reasonable | fused miss rate (%): 7.89 -> 7.36 | Improved |
| use strict labeling (IoU>0.7) instead of standard (IoU>0.5) for BCN (ablation) | SDS-RCNN · Caltech reasonable | fused miss rate (%): 8.71 -> 7.36 | Improved |
| use strict labeling for BCN (ablation) | SDS-RCNN BCN · Caltech reasonable | BCN miss rate (%): 17.41 -> 10.98 | Improved |
| share conv3 features between RPN and BCN instead of separate networks (ablation) | SDS-RCNN · Caltech reasonable | fused miss rate (%): 7.36 -> 8.66 | Hurt |
| share conv5 features between RPN and BCN (ablation) | SDS-RCNN · Caltech reasonable | fused miss rate (%): 7.36 -> 10.87 | Hurt |
Closest papers by meaning
- VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision (CVPR 2023 · similarity 0.89)
- Mask-Guided Attention Network for Occluded Pedestrian Detection (ICCV 2019 · similarity 0.89)
- Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving (CVPR 2023 · similarity 0.89)
- High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection (CVPR 2019 · similarity 0.88)
- Semantic Channels for Fast Pedestrian Detection (CVPR 2016 · similarity 0.87)
- Jointly Learning Deep Features, Deformable Parts, Occlusion and Classification for Pedestrian Detection (TPAMI 2017 · 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.
