CornerNet

2000년 도입 · 논문 7편에서 사용

CornerNet is an object detection model that detects 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. It also utilises corner pooling, a new type of pooling layer than helps the network better localize corners.

출처: CornerNet: Detecting Objects as Paired Keypoints

소개 논문: CornerNet: Detecting Objects as Paired Keypoints