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

Recently, large-scale pre-trained Vision and Language (VL) models have set anew state-of-the-art (SOTA) in zero-shot visual classification enablingopen-vocabulary recognition of potentially unlimited set of categories definedas simple language prompts. However, despite these great advances, theperformance of these zeroshot classifiers still falls short of the results ofdedicated (closed category set) classifiers trained with supervised finetuning. In this paper we show, for the first time, how to reduce this gapwithout any labels and without any paired VL data, using an unlabeled imagecollection and a set of texts auto-generated using a Large Language Model (LLM)describing the categories of interest and effectively substituting labeledvisual instances of those categories. Using our label-free approach, we areable to attain significant performance improvements over the zero-shotperformance of the base VL model and other contemporary methods and baselineson a wide variety of datasets, demonstrating absolute improvement of up to11.7% (3.8% on average) in the label-free setting. Moreover, despite ourapproach being label-free, we observe 1.3% average gains over leading few-shotprompting baselines that do use 5-shot supervision.

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections