Research map / Detection and segmentation / CNN features
Toward Scale-Invariance and Position-Sensitive Region Proposal Networks
Hsueh-Fu Lu, Xiaofei Du, Ping-Lin Chang
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 global convolutional network (GCN) head (ablation) | Baseline RPN · PASCAL VOC 07test | AR@1000: from 0.48 to 0.59 | Improved |
| add GCN head (ablation) | Baseline RPN · COCO minival | AR@1000: from 0.421 to 0.542 | Improved |
| add position-sensitive score maps (ablation) | Baseline RPN · PASCAL VOC 07test | AR@1000: from 0.480 to 0.605 (26%) | Improved |
| add position-sensitive score maps (ablation) | GCN-NS · PASCAL VOC 07test | AR@1000: from 0.586 to 0.653 (11%) | Improved |
| add position-sensitive score maps (ablation) | Baseline RPN · COCO minival | AR@1000: from 0.421 to 0.448 (6%) | Improved |
| add position-sensitive score maps (ablation) | GCN-NS · COCO minival | AR@1000: from 0.532 to 0.607 (14%) | Improved |
| add GCN-S head (ablation) | Baseline RPN · PASCAL VOC 07test | AR small @1000: from 0.254 to 0.471 (85%) | Improved |
| add GCN-NS head (ablation) | Baseline RPN · COCO minival | AR small @1000: from 0.308 to 0.422 (37%) | Improved |
| replace separable GCN with large plain kernel (LK-S) at similar parameter budget (ablation) | GCN-S · PASCAL VOC 07test | AR@1000: not as effective as GCN-S and GCN-NS models | Hurt |
| use separable-kernel GCN-S instead of Naive extra-CBR3 head (ablation) | Naive head · PASCAL VOC 07test | AR@1000: similar results | Improved |
| add position-sensitivity and GCN together (ablation) | Baseline RPN · PASCAL VOC 07test | AR@1000: 0.48 -> 0.65 (35%) | Improved |
| add position-sensitivity and GCN together (ablation) | Baseline RPN · COCO minival | AR@1000: 0.42 -> 0.61 (44%) | Improved |
Closest papers by meaning
- What Makes for Effective Detection Proposals? (TPAMI 2016 · similarity 0.91)
- HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection (CVPR 2016 · similarity 0.89)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016 · similarity 0.89)
- Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection (ECCV 2020 · similarity 0.88)
- You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection (CVPR 2019 · similarity 0.88)
- Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (TPAMI 2016 · 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.
