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

Out-of-distribution (OOD) detection is an important task in machine learningsystems for ensuring their reliability and safety. Deep probabilisticgenerative models facilitate OOD detection by estimating the likelihood of adata sample. However, such models frequently assign a suspiciously highlikelihood to a specific outlier. Several recent works have addressed thisissue by training a neural network with auxiliary outliers, which are generatedby perturbing the input data. In this paper, we discover that these approachesfail for certain OOD datasets. Thus, we suggest a new detection metric thatoperates without outlier exposure. We observe that our metric is robust todiverse variations of an image compared to the previous outlier-exposingmethods. Furthermore, our proposed score requires neither auxiliary models noradditional training. Instead, this paper utilizes the likelihood ratiostatistic in a new perspective to extract genuine properties from the givensingle deep probabilistic generative model. We also apply a novel numericalapproximation to enable fast implementation. Finally, we demonstratecomprehensive experiments on various probabilistic generative models and showthat our method achieves state-of-the-art performance.

Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models