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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep neural networks for image classification only learn to mapin-distribution inputs to their corresponding ground truth labels in trainingwithout differentiating out-of-distribution samples from in-distribution ones.This results from the assumption that all samples are independent andidentically distributed (IID) without distributional distinction. Therefore, apretrained network learned from in-distribution samples treatsout-of-distribution samples as in-distribution and makes high-confidencepredictions on them in the test phase. To address this issue, we drawout-of-distribution samples from the vicinity distribution of trainingin-distribution samples for learning to reject the prediction onout-of-distribution inputs. A \textit{Cross-class Vicinity Distribution} isintroduced by assuming that an out-of-distribution sample generated by mixingmultiple in-distribution samples does not share the same classes of itsconstituents. We thus improve the discriminability of a pretrained network byfinetuning it with out-of-distribution samples drawn from the cross-classvicinity distribution, where each out-of-distribution input corresponds to acomplementary label. Experiments on various in-/out-of-distribution datasetsshow that the proposed method significantly outperforms the existing methods inimproving the capacity of discriminating between in- and out-of-distributionsamples.

Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution Data