Search Results for author: Thomas Baltzer Moeslund

Found 2 papers, 0 papers with code

Distance in Latent Space as Novelty Measure

no code implementations31 Mar 2020 Mark Philip Philipsen, Thomas Baltzer Moeslund

Similarity is measured based on the Euclidean distance between samples in the latent space produced by a DNN.

Prediction Confidence from Neighbors

no code implementations31 Mar 2020 Mark Philip Philipsen, Thomas Baltzer Moeslund

Depending on the acceptable degree of error, predictions can either be trusted or rejected based on the distance to training samples.

Cannot find the paper you are looking for? You can Submit a new open access paper.