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

Deep neural networks achieve superior performance in challenging tasks suchas image classification. However, deep classifiers tend to incorrectly classifyout-of-distribution (OOD) inputs, which are inputs that do not belong to theclassifier training distribution. Several approaches have been proposed todetect OOD inputs, but the detection task is still an ongoing challenge. Inthis paper, we propose a new OOD detection approach that can be easily appliedto an existing classifier and does not need to have access to OOD samples. Thedetector is a one-class classifier trained on the output of an early layer ofthe original classifier fed with its original training set. We apply ourapproach to several low- and high-dimensional datasets and compare it to thestate-of-the-art detection approaches. Our approach achieves substantiallybetter results over multiple metrics.

Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output