Improving Novelty Detection using the Reconstructions of Nearest Neighbours. (arXiv:2111.06150v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2111.06150

We show that using nearest neighbours in the latent space of autoencoders
(AE) significantly improves performance of semi-supervised novelty detection in
both single and multi-class contexts. Autoencoding methods detect novelty by
learning to differentiate between the non-novel training class(es) and all
other unseen classes. Our method harnesses a combination of the reconstructions
of the nearest neighbours and the latent-neighbour distances of a given input's
latent representation. We demonstrate that our nearest-latent-neighbours (NLN)
algorithm is memory and time efficient, does not …

arxiv detection