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.
翻译:我们提议CornerNet, 这是一种新的物体探测方法, 即我们使用单一的 convolution 神经网络, 将物体捆绑盒作为一对关键点, 左上角和右下角, 来检测一个物体捆绑盒。 我们通过检测物体作为配对关键点, 消除了设计一套通常在以前的单级探测器中使用的锚箱的必要性。 除了我们的新配方外, 我们引入了角集成, 这是一种有助于网络更本地化角的新型集合层。 实验显示, CornerNet在 MS COCO 上取得了42.2%的AP, 超过了所有现有的单级探测器。