CornerNet: Detecting Objects as Paired Keypoints

Hei Law, Jia Deng

Research output: Contribution to journalArticlepeer-review

528 Scopus citations


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.

Original languageEnglish (US)
Pages (from-to)642-656
Number of pages15
JournalInternational Journal of Computer Vision
Issue number3
StatePublished - Mar 1 2020

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


  • Associative embedding
  • Hourglass network
  • Object detection


Dive into the research topics of 'CornerNet: Detecting Objects as Paired Keypoints'. Together they form a unique fingerprint.

Cite this