English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We tackle unsupervised anomaly detection (UAD), a problem of detecting datathat significantly differ from normal data. UAD is typically solved by usingdensity estimation. Recently, deep neural network (DNN)-based densityestimators, such as Normalizing Flows, have been attracting attention. However,one of their drawbacks is the difficulty in adapting them to the change in thenormal data's distribution. To address this difficulty, we propose AdaFlow, anew DNN-based density estimator that can be easily adapted to the change of thedistribution. AdaFlow is a unified model of a Normalizing Flow and AdaptiveBatch-Normalizations, a module that enables DNNs to adapt to new distributions.AdaFlow can be adapted to a new distribution by just conducting forwardpropagation once per sample; hence, it can be used on devices that have limitedcomputational resources. We have confirmed the effectiveness of the proposedmodel through an anomaly detection in a sound task. We also propose a method ofapplying AdaFlow to the unpaired cross-domain translation problem, in which onehas to train a cross-domain translation model with only unpaired samples. Wehave confirmed that our model can be used for the cross-domain translationproblem through experiments on image datasets.

AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation