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.
Source: CornerNet: Detecting Objects as Paired KeypointsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 6 | 66.67% |
Table Detection | 1 | 11.11% |
Table Recognition | 1 | 11.11% |
Decoder | 1 | 11.11% |
Component | Type |
|
---|---|---|
Corner Pooling
|
Pooling Operations | |
Stacked Hourglass Network
|
Pose Estimation Models |