One-Stage Object Detection Models
CornerNet
Introduced by Law et al. in CornerNet: Detecting Objects as Paired KeypointsCornerNet 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 Keypoints
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object | 6 | 40.00% |
| Object Detection | 6 | 40.00% |
| Table Detection | 1 | 6.67% |
| Table Recognition | 1 | 6.67% |
| Decoder | 1 | 6.67% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Corner Pooling
|
Pooling Operations | |
Stacked Hourglass Network
|
Pose Estimation Models |
