SnapMix<T>

Models & Types · AiDotNet.Augmentation.Image

SnapMix (Huang et al., 2021) - semantically proportional mixing for fine-grained recognition. Uses class activation map (CAM) inspired saliency for proportional label mixing.

Inheritance: AugmentationBase<T, ImageTensor<T>> → LabelMixingAugmentationBase<T, ImageTensor<T>> → ImageMixingAugmenterBase<T> → SnapMix<T>

Constructors

Constructor Summary
SnapMix(double alpha, double probability)

Methods

Method Summary
IDictionary<string, object> GetParameters()
ImageTensor<T> ApplySnapMix(ImageTensor<T> image1, ImageTensor<T> image2, Vector<T> labels1, Vector<T> labels2, AugmentationContext<T> context) Mixes two images using saliency-proportional mixing.