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.

@inproceedings{Law:2018:CDO,
   author = "Hei Law and Jia Deng",
   title = "{CornerNet}: Detecting Objects as Paired Keypoints",
   booktitle = "European Conference on Computer Vision (ECCV)",
   year = "2018",
   month = sep
}