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

Detecting out-of-distribution (OOD) inputs is critical for safely deployingdeep learning models in an open-world setting. However, existing OOD detectionsolutions can be brittle in the open world, facing various types of adversarialOOD inputs. While methods leveraging auxiliary OOD data have emerged, ouranalysis on illuminative examples reveals a key insight that the majority ofauxiliary OOD examples may not meaningfully improve or even hurt the decisionboundary of the OOD detector, which is also observed in empirical results onreal data. In this paper, we provide a theoretically motivated method,Adversarial Training with informative Outlier Mining (ATOM), which improves therobustness of OOD detection. We show that, by mining informative auxiliary OODdata, one can significantly improve OOD detection performance, and somewhatsurprisingly, generalize to unseen adversarial attacks. ATOM achievesstate-of-the-art performance under a broad family of classic and adversarialOOD evaluation tasks. For example, on the CIFAR-10 in-distribution dataset,ATOM reduces the FPR (at TPR 95%) by up to 57.99% under adversarial OOD inputs,surpassing the previous best baseline by a large margin.

ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining