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 consider a novel formulation of the problem of Active Few-ShotClassification (AFSC) where the objective is to classify a small, initiallyunlabeled, dataset given a very restrained labeling budget. This problem can beseen as a rival paradigm to classical Transductive Few-Shot Classification(TFSC), as both these approaches are applicable in similar conditions. We firstpropose a methodology that combines statistical inference, and an originaltwo-tier active learning strategy that fits well into this framework. We thenadapt several standard vision benchmarks from the field of TFSC. Ourexperiments show the potential benefits of AFSC can be substantial, with gainsin average weighted accuracy of up to 10% compared to state-of-the-art TFSCmethods for the same labeling budget. We believe this new paradigm could leadto new developments and standards in data-scarce learning settings.

Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings