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/

Zendy Plus

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

Zendy Tools

Zendy Open

As deep learning methods form a critical part in commercially importantapplications such as autonomous driving and medical diagnostics, it isimportant to reliably detect out-of-distribution (OOD) inputs while employingthese algorithms. In this work, we propose an OOD detection algorithm whichcomprises of an ensemble of classifiers. We train each classifier in aself-supervised manner by leaving out a random subset of training data as OODdata and the rest as in-distribution (ID) data. We propose a novel margin-basedloss over the softmax output which seeks to maintain at least a margin $m$between the average entropy of the OOD and in-distribution samples. Inconjunction with the standard cross-entropy loss, we minimize the novel loss totrain an ensemble of classifiers. We also propose a novel method to combine theoutputs of the ensemble of classifiers to obtain OOD detection score and classprediction. Overall, our method convincingly outperforms Hendrycks et al.[7]and the current state-of-the-art ODIN[13] on several OOD detection benchmarks.

Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers