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

Uncertainty estimation in deep learning has recently emerged as a crucialarea of interest to advance reliability and robustness in safety-criticalapplications. While there have been many proposed methods that either focus ondistance-aware model uncertainties for out-of-distribution detection or oninput-dependent label uncertainties for in-distribution calibration, both ofthese types of uncertainty are often necessary. In this work, we propose theHetSNGP method for jointly modeling the model and data uncertainty. We showthat our proposed model affords a favorable combination between these two typesof uncertainty and thus outperforms the baseline methods on some challengingout-of-distribution datasets, including CIFAR-100C, ImageNet-C, and ImageNet-A.Moreover, we propose HetSNGP Ensemble, an ensembled version of our method whichadditionally models uncertainty over the network parameters and outperformsother ensemble baselines.

Deep Classifiers with Label Noise Modeling and Distance Awareness