Nirvana Distance

版本 1.0.2 (2.1 KB) 作者: David Heise

This code computes the nirvana distance, or distance from "ideal" for a data augmentation.

关注

0.0

(0)

8.0 次下载

更新时间 2023/8/20

查看许可证

This function will calculate the nirvana distance -- that is, the distance from "ideal" -- for a data augmentation.

Inputs:

C - an integer matrix of the confusion data for the augmentation under evaluation, with ground truth labels in rows and predicted labels in columns

F - a square matrix representing the distances between target classes in the original (non-augmented) data feature space, with order of classes as in C

Outputs:

ND - the computed nirvana distance

dc - a vector of values representing the distance component for each target class in the data set

引用格式

D. Heise and H. Bear, "Evaluating the Potential and Realized Impact of Data Augmentations", submitted to 2023 IEEE Symposium Series on Computational Intelligence, in review.