DIoULoss<T>
Models & Types · AiDotNet.ComputerVision.Detection.Losses
Distance Intersection over Union (DIoU) loss for bounding box regression.
Inheritance: LossFunctionBase<T> → DIoULoss<T>
For Beginners
DIoU loss adds a center distance penalty to GIoU loss. This helps the model converge faster by explicitly minimizing the distance between predicted and target box centers.
How It Works
DIoU = IoU - d²/c², where d is the center distance and c is the enclosing diagonal. DIoU Loss = 1 - DIoU
Reference: Zheng et al., “Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression”, AAAI 2020
Constructors
| Constructor | Summary |
|---|---|
DIoULoss() |
Creates a new DIoU loss instance. |
Methods
| Method | Summary |
|---|---|
T CalculateLoss(Tensor<T> predicted, Tensor<T> targets) |
Calculates the DIoU loss between predicted and target bounding boxes. |
T CalculateLoss(Vector<T> predicted, Vector<T> actual) |
Calculates the DIoU loss between predicted and target bounding boxes. |
Tensor<T> ComputeTapeLoss(Tensor<T> predicted, Tensor<T> target) |
|
double CalculateLossForBox(BoundingBox<T> predicted, BoundingBox<T> target) |
Calculates DIoU loss for a pair of bounding boxes. |