Skip to main content

CornerNet: Detecting Objects as Paired Keypoints

Author(s): Law, Hei; Deng, Jia

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1353w
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.
Publication Date: 2020
Citation: Law, Hei, and Jia Deng. "CornerNet: Detecting Objects as Paired Keypoints." International Journal of Computer Vision 128, no. 3 (2020): pp. 642-656. doi:10.1007/s11263-019-01204-1
DOI: 10.1007/s11263-019-01204-1
ISSN: 0920-5691
EISSN: 1573-1405
Pages: 642 - 656
Type of Material: Journal Article
Journal/Proceeding Title: International Journal of Computer Vision
Version: Author's manuscript



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.