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

Recent works have shown that unstructured text (documents) from onlinesources can serve as useful auxiliary information for zero-shot imageclassification. However, these methods require access to a high-quality sourcelike Wikipedia and are limited to a single source of information. LargeLanguage Models (LLM) trained on web-scale text show impressive abilities torepurpose their learned knowledge for a multitude of tasks. In this work, weprovide a novel perspective on using an LLM to provide text supervision for azero-shot image classification model. The LLM is provided with a few textdescriptions from different annotators as examples. The LLM is conditioned onthese examples to generate multiple text descriptions for each class(referredto as views). Our proposed model, I2MVFormer, learns multi-view semanticembeddings for zero-shot image classification with these class views. We showthat each text view of a class provides complementary information allowing amodel to learn a highly discriminative class embedding. Moreover, we show thatI2MVFormer is better at consuming the multi-view text supervision from LLMcompared to baseline models. I2MVFormer establishes a new state-of-the-art onthree public benchmark datasets for zero-shot image classification withunsupervised semantic embeddings.

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification