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

Explaining to users why automated systems make certain mistakes is importantand challenging. Researchers have proposed ways to automatically produceinterpretations for deep neural network models. However, it is unclear howuseful these interpretations are in helping users figure out why they aregetting an error. If an interpretation effectively explains to users how theunderlying deep neural network model works, people who were presented with theinterpretation should be better at predicting the model's outputs than thosewho were not. This paper presents an investigation on whether or not showingmachine-generated visual interpretations helps users understand the incorrectlypredicted labels produced by image classifiers. We showed the images and thecorrect labels to 150 online crowd workers and asked them to select theincorrectly predicted labels with or without showing them the machine-generatedvisual interpretations. The results demonstrated that displaying the visualinterpretations did not increase, but rather decreased, the average guessingaccuracy by roughly 10%.

How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labels