Journal
INTERNATIONAL JOURNAL OF COMPUTER VISION
Volume 128, Issue 3, Pages 642-656Publisher
SPRINGER
DOI: 10.1007/s11263-019-01204-1
Keywords
Object detection; Associative embedding; Hourglass network
Categories
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available