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

Recent vision-language models outperform vision-only models on many imageclassification tasks. However, because of the absence of paired text/imagedescriptions, it remains difficult to fine-tune these models for fine-grainedimage classification. In this work, we propose a method, GIST, for generatingimage-specific fine-grained text descriptions from image-only datasets, andshow that these text descriptions can be used to improve classification. Keyparts of our method include 1. prompting a pretrained large language model withdomain-specific prompts to generate diverse fine-grained text descriptions foreach class and 2. using a pretrained vision-language model to match each imageto label-preserving text descriptions that capture relevant visual features inthe image. We demonstrate the utility of GIST by fine-tuning vision-languagemodels on the image-and-generated-text pairs to learn an alignedvision-language representation space for improved classification. We evaluateour learned representation space in full-shot and few-shot scenarios acrossfour diverse fine-grained classification datasets, each from a differentdomain. Our method achieves an average improvement of $4.1\%$ in accuracy overCLIP linear probes and an average of $1.1\%$ improvement in accuracy over theprevious state-of-the-art image-text classification method on the full-shotdatasets. Our method achieves similar improvements across few-shot regimes.Code is available at https://github.com/emu1729/GIST.

GIST: Generating Image-Specific Text for Fine-grained Object Classification