Papers › CornerNet: Detecting Objects as Paired Keypoints
CornerNet: Detecting Objects as Paired Keypoints
Hei Law, Jia Deng
We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-stage detectors.
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="1808.01244")
Code
Syntology Ran 3 of 11 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong.
By repository: official repository: 11 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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; 3 ran; 1 honoured the contract we drafted; 8 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.
Licence: 0 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 princeton-vl/CornerNet. “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.
09a07cdf34e60fa0 · report
07caa911e46fcb23 · report
c2515898895b1abb · report
61bf3906cbd2ee87 · report
4d2829871f321cca · report
64475ebc43c0a3ea · report
74bee3912d0b766e · report
b859f01af13f1c20 · report
26448a43d8f15aeb · report
4c7015c577141603 · report
08aa371b972a4c91 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Detection | COCO minival | CornerNet511 (Hourglass-104) | AP50 | 53.8 | #197 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | CornerNet511 (Hourglass-104) | AP75 | 40.9 | #197 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | CornerNet511 (Hourglass-104) | APL | 51.8 | #197 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | CornerNet511 (Hourglass-104) | APM | 40.5 | #197 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | CornerNet511 (Hourglass-104) | APS | 18.6 | #197 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | CornerNet511 (Hourglass-104) | box AP | 38.4 | #197 of 220 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-104, multi-scale) | AP50 | 57.8 | #176 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-104, multi-scale) | AP75 | 45.3 | #176 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-104, multi-scale) | APL | 56.7 | #176 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-104, multi-scale) | APM | 44.8 | #176 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-104, multi-scale) | APS | 20.8 | #176 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-104, multi-scale) | box mAP | 42.1 | #176 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-52, single-scale) | AP50 | 53.7 | #216 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-52, single-scale) | AP75 | 40.1 | #216 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-52, single-scale) | APL | 50.5 | #216 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-52, single-scale) | APM | 39.0 | #216 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-52, single-scale) | APS | 17.0 | #216 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | CornerNet511 (Hourglass-52, single-scale) | box mAP | 37.8 | #216 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: CornerNet
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