Papers › CenterNet: Keypoint Triplets for Object Detection

CenterNet: Keypoint Triplets for Object Detection

17 Apr 2019ICCV 2019 10arXiv:1904.08189archive 2025-07-28

Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, Qi Tian

In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visual patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by at least 4.9%. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/Duankaiwen/CenterNet.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.08189")

Code

Syntology Ran 2 of 11 code samples harvested from 3 repositories linked to this paper; 9 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 0 ran; community (archive-listed): 8 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

20 repositories listed; official and paper-mentioned ones first.

Duankaiwen/CenterNet officialmentioned in papermentioned on GitHubpytorch report
DaiJianBo/CenterNet-duan-2080Ti mentioned on GitHubpytorchMIT report
guohaoyuan/CenterNet-annotation mentioned on GitHubpytorch report
jiajunhua/Duankaiwen-CenterNet mentioned on GitHubpytorch report
kuku-sichuan/CenterNet mentioned on GitHubtf report
lizhe960118/HrCenterNet mentioned on GitHubpytorch report
mv-lab/kuzushiji-recognition mentioned on GitHubpytorch report
takooctopus/CenterNet-Tako mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 2 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
9unverified

Licence: 2 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

make_br_layer Duankaiwen/CenterNet/models/CenterNet-104.py official repository unverified MIT (permissive) · afbdac6bd6565e40 · report
make_ct_layer Duankaiwen/CenterNet/models/CenterNet-104.py official repository unverified MIT (permissive) · c19e9cf52cc14141 · report
make_tl_layer Duankaiwen/CenterNet/models/CenterNet-104.py official repository unverified MIT (permissive) · 40baa01cf3e15e06 · report
make_layer_revr DaiJianBo/CenterNet-duan-2080Ti/models/py_utils/utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 09a07cdf34e60fa0 · report
make_merge_layer DaiJianBo/CenterNet-duan-2080Ti/models/py_utils/kp_utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 07caa911e46fcb23 · report
data_parallel DaiJianBo/CenterNet-duan-2080Ti/models/py_utils/data_parallel.py community (archive-listed) unverified MIT (permissive) · 61bf3906cbd2ee87 · report
hourglass104 kuku-sichuan/CenterNet/model/model.py community (archive-listed) unverified no licence file found · pointer only · ddc0ad11425f2ffe · report
hourglass50 kuku-sichuan/CenterNet/model/model.py community (archive-listed) unverified no licence file found · pointer only · b52a7eff88e625d0 · report
make_layer DaiJianBo/CenterNet-duan-2080Ti/models/py_utils/utils.py community (archive-listed) unverified MIT (permissive) · 74bee3912d0b766e · report
scatter DaiJianBo/CenterNet-duan-2080Ti/models/py_utils/scatter_gather.py community (archive-listed) unverified MIT (permissive) · 4c7015c577141603 · report
scatter_kwargs DaiJianBo/CenterNet-duan-2080Ti/models/py_utils/scatter_gather.py community (archive-listed) unverified MIT (permissive) · 08aa371b972a4c91 · report

Tasks

ObjectObject Detectionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival CenterNet511 (Hourglass-52) AP50 59.2 #167 of 220 Archive leaderboard report
Object Detection COCO minival CenterNet511 (Hourglass-52) AP75 43.9 #167 of 220 Archive leaderboard report
Object Detection COCO minival CenterNet511 (Hourglass-52) APL 55.8 #167 of 220 Archive leaderboard report
Object Detection COCO minival CenterNet511 (Hourglass-52) APM 43.8 #167 of 220 Archive leaderboard report
Object Detection COCO minival CenterNet511 (Hourglass-52) APS 23.6 #167 of 220 Archive leaderboard report
Object Detection COCO minival CenterNet511 (Hourglass-52) box AP 41.3 #167 of 220 Archive leaderboard report
Object Detection COCO test-dev CenterNet511 (Hourglass-104, multi-scale) AP50 64.5 #121 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet511 (Hourglass-104, multi-scale) AP75 50.7 #121 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet511 (Hourglass-104, multi-scale) APL 58.9 #121 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet511 (Hourglass-104, multi-scale) APM 49.9 #121 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet511 (Hourglass-104, multi-scale) APS 28.9 #121 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet511 (Hourglass-104, multi-scale) box mAP 47.0 #121 of 225 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Cascade Corner Pooling, Center Pooling, CenterNet

1x1 ConvolutionAdamBatch NormalizationCascade Corner PoolingCenter PoolingCenterNetConvolutionCorner PoolingCornerNetDLAFocal LossHourglass ModuleMax PoolingRandom Horizontal FlipReLUResidual ConnectionSoft-NMSStacked Hourglass NetworkStep Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections