CornerNet: Detecting Objects as Paired Keypoints

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 the corners. Experiments show that CornerNet achieves a 42.1% AP on MS COCO, outperforming all existing one-stage detectors.

Cite

Text

Law and Deng. "CornerNet: Detecting Objects as Paired Keypoints." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01264-9_45

Markdown

[Law and Deng. "CornerNet: Detecting Objects as Paired Keypoints." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/law2018eccv-cornernet/) doi:10.1007/978-3-030-01264-9_45

BibTeX

@inproceedings{law2018eccv-cornernet,
  title     = {{CornerNet: Detecting Objects as Paired Keypoints}},
  author    = {Law, Hei and Deng, Jia},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01264-9_45},
  url       = {https://mlanthology.org/eccv/2018/law2018eccv-cornernet/}
}