Dense anomaly detection by robust learning on synthetic negative data

#artificialintelligence 

We use T 10 for max-softmax and T 2 for divergence-based scoring functions. We report average performance over last three epochs. Row 1 shows the standard setting where the loss function is KL divergence between the uniform distribution and the softmax output Lee et al.; Hendrycks et al. while the anomaly score is max-softmax. Row 3 features the reversed KL divergence. Minimizing the reversed divergence between the uniform distribution and the softmax distribution is equivalent to maximizing the softmax entropy.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found