AI Paper Atlas

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

ICCV 2019 · Detection and segmentation › CNN features · approach: Box regression and loss design · 4,213 citations (OpenAlex)

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 changedWhereMeasuredEffect
add central region exploration (center keypoint triplet) (ablation)CornerNet511-52 · MS-COCO valAP (%): 37.6 -> 39.9Improved
add central region exploration (ablation)CornerNet511-52 · MS-COCO valAP large (%): 52.2 -> 52.3No clear effect
add center pooling (ablation)CornerNet511-52 + CRE · MS-COCO valAP (%): 39.9 -> 40.8Improved
add center pooling (ablation)CornerNet511-52 + CRE · MS-COCO valAP large (%): 52.2 -> 53.6Improved
add cascade corner pooling (ablation)CornerNet511-52 · MS-COCO valAP (%): 37.6 -> 38.3Improved
add cascade corner pooling (ablation)CenterNet511-52 (CRE + CTP) · MS-COCO valAP (%): 40.8 -> 41.3Improved
add cascade corner pooling (ablation)CornerNet511-52 · MS-COCO valAP large (%): 52.2 -> 52.2No clear effect
add cascade corner pooling (ablation)CenterNet511-52 (CRE + CTP) · MS-COCO valAP large (%): 53.6 -> 55.8Improved
replace CornerNet with CenterNet (add center keypoint, center pooling, cascade corner pooling)CornerNet511 Hourglass-52, single-scale · MS-COCO test-devAP (%): 37.8 -> 41.6Improved
replace CornerNet with CenterNetCornerNet511 Hourglass-104, multi-scale · MS-COCO test-devAP (%): 42.1 -> 47.0Improved
replace CornerNet with CenterNetCornerNet511-52, small objects, single-scale · MS-COCO test-devAP small (%): 17.0 -> 22.5Improved
add CenterNet center keypoint verificationCornerNet511-52 · MS-COCO valfalse discovery rate FD5 (%): 35.2 -> 30.7Improved

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.

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.

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