## Corner Pooling

Introduced by Law et al. in CornerNet: Detecting Objects as Paired Keypoints

Corner Pooling is a pooling technique for object detection that seeks to better localize corners by encoding explicit prior knowledge. Suppose we want to determine if a pixel at location $\left(i, j\right)$ is a top-left corner. Let $f_{t}$ and $f_{l}$ be the feature maps that are the inputs to the top-left corner pooling layer, and let $f_{t_{ij}}$ and $f_{l_{ij}}$ be the vectors at location $\left(i, j\right)$ in $f_{t}$ and $f_{l}$ respectively. With $H \times W$ feature maps, the corner pooling layer first max-pools all feature vectors between $\left(i, j\right)$ and $\left(i, H\right)$ in $f_{t}$ to a feature vector $t_{ij}$ , and max-pools all feature vectors between $\left(i, j\right)$ and $\left(W, j\right)$ in $f_{l}$ to a feature vector $l_{ij}$. Finally, it adds $t_{ij}$ and $l_{ij}$ together.

#### Latest Papers

PAPER DATE
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
| Cheng ChiFangyun WeiHan Hu
2020-10-29
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
| Zhiwei DongGuoxuan LiYue LiaoFei WangPengju RenChen Qian
2020-03-20
MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
| Abdullah RashwanRishav AgarwalAgastya KalraPascal Poupart
2020-01-09
CornerNet-Lite: Efficient Keypoint Based Object Detection
| Hei LawYun TengOlga RussakovskyJia Deng
2019-04-18
CenterNet: Keypoint Triplets for Object Detection
| Kaiwen DuanSong BaiLingxi XieHonggang QiQingming HuangQi Tian
2019-04-17
Bottom-up Object Detection by Grouping Extreme and Center Points
| Xingyi ZhouJiacheng ZhuoPhilipp Krähenbühl
2019-01-23
CornerNet: Detecting Objects as Paired Keypoints
| Hei LawJia Deng
2018-08-03