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 42.1% AP on MS COCO, outperforming all existing one-stage detectors.
Law, Hei, Deng, Jia
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 42.1% AP on MS COCO, outperforming all existing one-stage detectors.
https://arxiv.org/abs/1808.01244