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 focus on the challenge of out-of-distribution (OOD) detection in deeplearning models, a crucial aspect in ensuring reliability. Despite considerableeffort, the problem remains significantly challenging in deep learning modelsdue to their propensity to output over-confident predictions for OOD inputs. Wepropose a novel one-class open-set OOD detector that leverages text-imagepre-trained models in a zero-shot fashion and incorporates various descriptionsof in-domain and OOD. Our approach is designed to detect anything not in-domainand offers the flexibility to detect a wide variety of OOD, defined via fine-or coarse-grained labels, or even in natural language. We evaluate our approachon challenging benchmarks including large-scale datasets containingfine-grained, semantically similar classes, distributionally shifted images,and multi-object images containing a mixture of in-domain and OOD objects. Ourmethod shows superior performance over previous methods on all benchmarks. Codeis available at https://github.com/gyhandy/One-Class-Anything

Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models