CornerNet-Squeeze Hourglass is a convolutional neural network and object detection backbone used in the CornerNet-Squeeze object detector. It uses a modified hourglass module that makes use of a fire module: containing 1x1 convolutions and depthwise convolutions.
Source: CornerNet-Lite: Efficient Keypoint Based Object DetectionPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
Convolution
|
Convolutions | |
CornerNet-Squeeze Hourglass Module
|
Image Model Blocks |