Object Detection Models
CornerNet-Saccade
Introduced by Law et al. in CornerNet-Lite: Efficient Keypoint Based Object DetectionCornerNet-Saccade is an extension of CornerNet with an attention mechanism similar to saccades in human vision. It starts with a downsized full image and generates an attention map, which is then zoomed in on and processed further by the model. This differs from the original CornerNet in that it is applied fully convolutionally across multiple scales.
Source: CornerNet-Lite: Efficient Keypoint Based Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
1x1 Convolution
Convolution
Corner Pooling
ReLU
Sigmoid Activation
Soft-NMS
Stacked Hourglass Network
