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

Humans can obtain the knowledge of novel visual concepts from languagedescriptions, and we thus use the few-shot image classification task toinvestigate whether a machine learning model can have this capability. Ourproposed model, LIDE (Learning from Image and DEscription), has a text decoderto generate the descriptions and a text encoder to obtain the textrepresentations of machine- or user-generated descriptions. We confirmed thatLIDE with machine-generated descriptions outperformed baseline models.Moreover, the performance was improved further with high-quality user-generateddescriptions. The generated descriptions can be viewed as the explanations ofthe model's predictions, and we observed that such explanations were consistentwith prediction results. We also investigated why the language descriptionimproved the few-shot image classification performance by comparing the imagerepresentations and the text representations in the feature spaces.

Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions