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) inputs is a central challenge for safelydeploying machine learning models in the real world. Existing solutions aremainly driven by small datasets, with low resolution and very few class labels(e.g., CIFAR). As a result, OOD detection for large-scale image classificationtasks remains largely unexplored. In this paper, we bridge this critical gap byproposing a group-based OOD detection framework, along with a novel OOD scoringfunction termed MOS. Our key idea is to decompose the large semantic space intosmaller groups with similar concepts, which allows simplifying the decisionboundaries between in- vs. out-of-distribution data for effective OODdetection. Our method scales substantially better for high-dimensional classspace than previous approaches. We evaluate models trained on ImageNet againstfour carefully curated OOD datasets, spanning diverse semantics. MOSestablishes state-of-the-art performance, reducing the average FPR95 by 14.33%while achieving 6x speedup in inference compared to the previous best method.

MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space