Research map / Detection and segmentation / CNN features
CenterNet: Keypoint Triplets for Object Detection
Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, Qi Tian
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 central region exploration (center keypoint triplet) (ablation) | CornerNet511-52 · MS-COCO val | AP (%): 37.6 -> 39.9 | Improved |
| add central region exploration (ablation) | CornerNet511-52 · MS-COCO val | AP large (%): 52.2 -> 52.3 | No clear effect |
| add center pooling (ablation) | CornerNet511-52 + CRE · MS-COCO val | AP (%): 39.9 -> 40.8 | Improved |
| add center pooling (ablation) | CornerNet511-52 + CRE · MS-COCO val | AP large (%): 52.2 -> 53.6 | Improved |
| add cascade corner pooling (ablation) | CornerNet511-52 · MS-COCO val | AP (%): 37.6 -> 38.3 | Improved |
| add cascade corner pooling (ablation) | CenterNet511-52 (CRE + CTP) · MS-COCO val | AP (%): 40.8 -> 41.3 | Improved |
| add cascade corner pooling (ablation) | CornerNet511-52 · MS-COCO val | AP large (%): 52.2 -> 52.2 | No clear effect |
| add cascade corner pooling (ablation) | CenterNet511-52 (CRE + CTP) · MS-COCO val | AP large (%): 53.6 -> 55.8 | Improved |
| replace CornerNet with CenterNet (add center keypoint, center pooling, cascade corner pooling) | CornerNet511 Hourglass-52, single-scale · MS-COCO test-dev | AP (%): 37.8 -> 41.6 | Improved |
| replace CornerNet with CenterNet | CornerNet511 Hourglass-104, multi-scale · MS-COCO test-dev | AP (%): 42.1 -> 47.0 | Improved |
| replace CornerNet with CenterNet | CornerNet511-52, small objects, single-scale · MS-COCO test-dev | AP small (%): 17.0 -> 22.5 | Improved |
| add CenterNet center keypoint verification | CornerNet511-52 · MS-COCO val | false discovery rate FD5 (%): 35.2 -> 30.7 | Improved |
Later papers that compared with this method
1 later accepted paper reports CenterNet511-104 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection (CVPR 2020 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CornerNet511-52 — CornerNet: Detecting Objects as Paired Keypoints (ECCV 2018) · better on 4 of 4 shared results
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
- CenterNet++ for Object Detection (TPAMI 2023 · similarity 0.95)
- CornerNet: Detecting Objects as Paired Keypoints (ECCV 2018 · similarity 0.90)
- CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection (CVPR 2020 · similarity 0.90)
- Corner Proposal Network for Anchor-free, Two-stage Object Detection (ECCV 2020 · similarity 0.88)
- Center-Based 3D Object Detection and Tracking (CVPR 2021 · similarity 0.87)
- SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection (AAAI 2024 · 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.
