AI Paper Atlas

Research map / Detection and segmentation / CNN features

CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection

Zhiwei Dong, Guoxuan Li, Yue Liao, Fei Wang, Pengju Ren, Chen Qian

CVPR 2020 · Detection and segmentation › CNN features · approach: Joint detection and instance segmentation · 184 citations (OpenAlex)

Check 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 changedWhereMeasuredEffect
Replace associative embedding with centripetal shift matching (ablation)CornerNet · MS-COCO test-dev, CornerNet matching ablationAP: 37.5 -> 40.7Improved
Add center prediction and CenterNet matching (ablation)CornerNet · MS-COCO test-dev, CornerNet matching ablationAP: 37.5 -> 39.9Improved
Replace associative embedding with center regression (ablation)CornerNet · MS-COCO test-dev, CornerNet matching ablationAP: 37.5 -> 40.1Improved
Add standard deformable convolution (ablation)CentripetalNet without feature adaptation or mask head · MS-COCO test-dev, feature adaptation ablationAP: 40.7 -> 40.8Improved
Use RoI convolution for feature adaptation (ablation)CentripetalNet without feature adaptation or mask head · MS-COCO test-dev, feature adaptation ablationAP: 40.7 -> 41.1Improved
Add cross-star deformable convolution guided by corner-to-center shifts (ablation)CentripetalNet without feature adaptation or mask head · MS-COCO test-dev, feature adaptation ablationAP: 40.7 -> 41.5Improved
Add the mask prediction module (ablation)CentripetalNet · MS-COCO test-dev, 110 epochsAP: 41.5 -> 41.8Improved
Add the mask prediction module (ablation)CentripetalNet · MS-COCO test-dev, 210 epochsAP: 41.7 -> 42.1Improved
Add a mask prediction module (ablation)CornerNet · MS-COCO test-dev, 110 epochsAP: 37.3 -> 37.3No clear effect
Use multi-scale rather than single-scale testingCentripetalNet · MS-COCO test-dev2017 object detectionAP: 46.1 -> 48.0Improved

Later papers that compared with this method

3 later accepted papers report CentripetalNet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy