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

Recognizing out-of-distribution (OOD) samples is critical for machinelearning systems deployed in the open world. The vast majority of OOD detectionmethods are driven by a single modality (e.g., either vision or language),leaving the rich information in multi-modal representations untapped. Inspiredby the recent success of vision-language pre-training, this paper enriches thelandscape of OOD detection from a single-modal to a multi-modal regime.Particularly, we propose Maximum Concept Matching (MCM), a simple yet effectivezero-shot OOD detection method based on aligning visual features with textualconcepts. We contribute in-depth analysis and theoretical insights tounderstand the effectiveness of MCM. Extensive experiments demonstrate that MCMachieves superior performance on a wide variety of real-world tasks. MCM withvision-language features outperforms a common baseline with pure visualfeatures on a hard OOD task with semantically similar classes by 13.1% (AUROC).Code is available at https://github.com/deeplearning-wisc/MCM.

Delving into Out-of-Distribution Detection with Vision-Language Representations