Home
SeHoon
Cancel

ROS

What is ROS(Robot Operating System)? ROS provides various libraries and tools for implementation and debugging. As the name suggests, you might think that ROS is an Operating System. However, more...

Cost Function

What is cost function? A cost function is a function that needs to be minimized or maximized in an optimization algorithm in machine learning. Gradient descent is a basic algorithm used to minimiz...

SPP(Spatial Pyramid Pooling)

What is SPP? SPP allows CNN to be applied regardless of the size of the input image. Now, let’s see how SPP works. First, SPP takes the feature map extracted through the Conv Layers as input and ...

YOLOv5

What is YOLOv5? YOLOv5 is almost the same as YOLOv4 but has been upgraded. Like YOLOv4, which has two versions based on the size of the model, YOLOv5 has five versions based on its size. ...

CSP(Cross Stage Partial Connections)

What is CSP? CSP is a concept designed to reduce the amount of computation while enabling multiple gradient combinations. As a solution, the input to a dense block of CSP is divided into two parts....

CIOU loss(Complete IoU)

What is CIOU loss? CIOU introduces two new concepts compared to IOU loss. The concept of centroid distance, which is the distance between the centroid of the actual bounding box and the ce...

IOU loss

What is IOU loss? IOU is a method to address the disadvantage of L2 Regularization which tends to minimize the error of small objects and maximize the error of big objects. The IoU loss considers t...

scaled-YOLOv4

What is scaled-YOLOv4? Scaled-YOLOv4 is designed to be used on every device, whether they are low-end or high-end. Additionally, it can perform real-time object detection on 16, 30, and 60 FPS vid...

DropBlock

What is DropBlock? It is a way to perform Regularization. It is almost same as Dropout. However, there is a key difference: DropBlock drops random ‘blocks’ of features to address the disadvantages ...

YOLOv4

What is YOLOv4? YOLOv4 addresses the disadvantages of R-CNN, which has low FPS and does not require fixed-size input images because of SPP(Spatial Pyramid Pooling). However, YOLOv4 is not as a...