Research map / Detection and segmentation / CNN features
RepPoints: Point Set Representation for Object Detection
Ze Yang, Shaohui Liu, Han Hu, Liwei Wang, Stephen Lin
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 |
|---|---|---|---|
| replace bounding box with RepPoints representation (ablation) | two-stage detector (ResNet-50) · COCO minival | AP: +2.1 mAP | Improved |
| replace bounding box with RepPoints representation (ablation) | two-stage detector (ResNet-101) · COCO minival | AP: +2.0 mAP | Improved |
| add object localization loss to RepPoints learning (ablation) | RPDet · COCO minival | AP: 33.8 -> 38.3 | Improved |
| add recognition loss feedback to RepPoints learning (ablation) | RPDet · COCO minival | AP: 37.6 -> 38.3 | Improved |
| add recognition loss feedback to bounding box detector (ablation) | bounding box detector · COCO minival | AP: 36.2 -> 36.2 | No clear effect |
| use center point instead of single anchor as initial representation (ablation) | bounding box detector · COCO minival | AP: 36.2 -> 37.3 | Improved |
| use center point instead of single anchor as initial representation (ablation) | RepPoints detector · COCO minival | AP: 36.9 -> 38.3 | Improved |
| use moment-based instead of min-max pseudo box conversion (ablation) | RPDet · COCO minival | AP: 38.2 -> 38.3 | No clear effect |
| add deformable RoI pooling on first-stage proposals (ablation) | bounding box detector · COCO minival | AP: 36.2 -> 36.9 | Improved |
| add deformable RoI pooling on first-stage proposals (ablation) | RPDet · COCO minival | AP: 38.3 -> 39.1 | Improved |
| replace YOLO-like anchor-free detector with RepPoints | anchor-free detector (ResNet-50) · COCO minival | AP: 33.9 -> 38.3 | Improved |
| replace multi-anchor RetinaNet with RPDet | ResNet-50 detector · COCO minival | AP: 35.7 -> 38.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Cascade R-CNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · better on 1 of 1 shared result
- CornerNet — CornerNet: Detecting Objects as Paired Keypoints (ECCV 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RepPoints v2: Verification Meets Regression for Object Detection (NeurIPS 2020 · similarity 0.93)
- Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation (ECCV 2020 · similarity 0.88)
- CPR++: Object Localization via Single Coarse Point Supervision (TPAMI 2024 · similarity 0.88)
- Weakly Supervised Object Localization and Detection: A Survey (TPAMI 2021 · similarity 0.87)
- PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object Detection (ICLR 2021 · similarity 0.87)
- PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection (ICLR 2025 · similarity 0.85)
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.
