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

We propose a simple, efficient, and accurate method for detectingout-of-distribution (OOD) data for trained neural networks. We propose a noveldescriptor, HAct - activation histograms, for OOD detection, that is,probability distributions (approximated by histograms) of output values ofneural network layers under the influence of incoming data. We formulate an OODdetector based on HAct descriptors. We demonstrate that HAct is significantlymore accurate than state-of-the-art in OOD detection on multiple imageclassification benchmarks. For instance, our approach achieves a true positiverate (TPR) of 95% with only 0.03% false-positives using Resnet-50 on standardOOD benchmarks, outperforming previous state-of-the-art by 20.67% in the falsepositive rate (at the same TPR of 95%). The computational efficiency and theease of implementation makes HAct suitable for online implementation inmonitoring deployed neural networks in practice at scale.

HAct: Out-of-Distribution Detection with Neural Net Activation Histograms