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

Vision and Language Models (VLMs), such as CLIP, have enabled visualrecognition of a potentially unlimited set of categories described by textprompts. However, for the best visual recognition performance, these modelsstill require tuning to better fit the data distributions of the downstreamtasks, in order to overcome the domain shift from the web-based pre-trainingdata. Recently, it has been shown that it is possible to effectively tune VLMswithout any paired data, and in particular to effectively improve VLMs visualrecognition performance using text-only training data generated by LargeLanguage Models (LLMs). In this paper, we dive deeper into this excitingtext-only VLM training approach and explore ways it can be significantlyfurther improved taking the specifics of the downstream task into account whensampling text data from LLMs. In particular, compared to the SOTA text-only VLMtraining approach, we demonstrate up to 8.4% performance improvement in (cross)domain-specific adaptation, up to 8.7% improvement in fine-grained recognition,and 3.1% overall average improvement in zero-shot classification compared tostrong baselines.

TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification