SaliencyMix<T>
Models & Types · AiDotNet.Augmentation.Image
SaliencyMix - saliency-guided image mixing that pastes salient regions. Uses simple gradient-based saliency estimation.
Inheritance: AugmentationBase<T, ImageTensor<T>> → LabelMixingAugmentationBase<T, ImageTensor<T>> → ImageMixingAugmenterBase<T> → SaliencyMix<T>
Constructors
| Constructor | Summary |
|---|---|
SaliencyMix(double alpha, double probability) |
Methods
| Method | Summary |
|---|---|
IDictionary<string, object> GetParameters() |
|
ImageTensor<T> ApplySaliencyMix(ImageTensor<T> image1, ImageTensor<T> image2, Vector<T> labels1, Vector<T> labels2, AugmentationContext<T> context) |
Mixes two images using saliency-guided selection of the paste region. |