Methods › Computer Vision › One-Stage Object Detection Models › CornerNet
CornerNet
Introduced by Hei Law et al. in CornerNet: Detecting Objects as Paired Keypoints
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
CornerNet is an object detection model that detects 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. It also utilises corner pooling, a new type of pooling layer than helps the network better localize corners.
Papers archive 2025-07-28
7 shown of 7, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Robust Table Detection and Structure Recognition from Heterogeneous Document Images 17 Mar 2022 · 0 repositories · arXiv:2203.09056
-
TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases 19 Apr 2021 · 0 repositories · arXiv:2104.09123
-
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder 29 Oct 2020 · 4 repositories · arXiv:2010.15831Syntology ran 0 of 5 samples · 5 unverified
-
MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection 9 Jan 2020 · 1 repository · arXiv:2001.03194
-
CenterNet: Keypoint Triplets for Object Detection 17 Apr 2019 · 20 repositories · arXiv:1904.08189Syntology ran 2 of 11 samples · 9 unverified · 2 pointer-only (licence)
-
Bottom-up Object Detection by Grouping Extreme and Center Points 23 Jan 2019 · 2 repositories · arXiv:1901.08043Syntology ran 1 of 5 samples · 4 unverified
-
CornerNet: Detecting Objects as Paired Keypoints 3 Aug 2018 · 5 repositories · arXiv:1808.01244Syntology ran 3 of 11 samples · 8 unverified
Tasks archive 2025-07-28
9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Object | 6 |
| Object Detection | 6 |
| object-detection | 6 |
| Decoder | 1 |
| Keypoint Estimation | 1 |
| Region Proposal | 1 |
| Table Detection | 1 |
| Table Recognition | 1 |
| Triplet | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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