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

Detecting out-of-distribution (OOD) data is crucial for ensuring the safedeployment of machine learning models in real-world applications. However,existing OOD detection approaches primarily rely on the feature maps or thefull gradient space information to derive OOD scores neglecting the role ofmost important parameters of the pre-trained network over in-distribution (ID)data. In this study, we propose a novel approach called GradOrth to facilitateOOD detection based on one intriguing observation that the important featuresto identify OOD data lie in the lower-rank subspace of in-distribution (ID)data. In particular, we identify OOD data by computing the norm of gradientprojection on the subspaces considered important for the in-distribution data.A large orthogonal projection value (i.e. a small projection value) indicatesthe sample as OOD as it captures a weak correlation of the ID data. This simpleyet effective method exhibits outstanding performance, showcasing a notablereduction in the average false positive rate at a 95% true positive rate(FPR95) of up to 8% when compared to the current state-of-the-art methods.

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients