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

When presented with Out-of-Distribution (OOD) examples, deep neural networksyield confident, incorrect predictions. Detecting OOD examples is challenging,and the potential risks are high. In this paper, we propose to detect OODexamples by identifying inconsistencies between activity patterns and classpredicted. We find that characterizing activity patterns by Gram matrices andidentifying anomalies in gram matrix values can yield high OOD detection rates.We identify anomalies in the gram matrices by simply comparing each value withits respective range observed over the training data. Unlike many approaches,this can be used with any pre-trained softmax classifier and does not requireaccess to OOD data for fine-tuning hyperparameters, nor does it require OODaccess for inferring parameters. The method is applicable across a variety ofarchitectures and vision datasets and, for the important and surprisingly hardtask of detecting far-from-distribution out-of-distribution examples, itgenerally performs better than or equal to state-of-the-art OOD detectionmethods (including those that do assume access to OOD examples).

Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices