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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In an out-of-distribution (OOD) detection problem, samples of knownclasses(also called in-distribution classes) are used to train a specialclassifier. In testing, the classifier can (1) classify the test samples ofknown classes to their respective classes and also (2) detect samples that donot belong to any of the known classes (i.e., they belong to some unknown orOOD classes). This paper studies the problem of zero-shotout-of-distribution(OOD) detection, which still performs the same two tasks intesting but has no training except using the given known class names. Thispaper proposes a novel yet simple method (called ZOC) to solve the problem. ZOCbuilds on top of the recent advances in zero-shot classification throughmulti-modal representation learning. It first extends the pre-trainedlanguage-vision model CLIP by training a text-based image description generatoron top of CLIP. In testing, it uses the extended model to generate candidateunknown class names for each test sample and computes a confidence score basedon both the known class names and candidate unknown class names for zero-shotOOD detection. Experimental results on 5 benchmark datasets for OOD detectiondemonstrate that ZOC outperforms the baselines by a large margin.

Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP