CornerNet: Detecting Objects as Paired Keypoints

Code

• github.com/princeton-vl/CornerNet
  OfficialIn paperpytorch★ 0
• github.com/gau-nernst/CenterNet
  pytorch★ 71
• github.com/egeonat/MS-CornerNet
  pytorch★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions