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

Human observers engage in selective information uptake when classifyingvisual patterns. The same is true of deep neural networks, which currentlyconstitute the best performing artificial vision systems. Our goal is toexamine the congruence, or lack thereof, in the information-gatheringstrategies of the two systems. We have operationalized our investigation as acharacter recognition task. We have used eye-tracking to assay the spatialdistribution of information hotspots for humans via fixation maps and anactivation mapping technique for obtaining analogous distributions for deepnetworks through visualization maps. Qualitative comparison betweenvisualization maps and fixation maps reveals an interesting correlate ofcongruence. The deep learning model considered similar regions in character,which humans have fixated in the case of correctly classified characters. Onthe other hand, when the focused regions are different for humans and deepnets, the characters are typically misclassified by the latter. Hence, wepropose to use the visual fixation maps obtained from the eye-trackingexperiment as a supervisory input to align the model's focus on relevantcharacter regions. We find that such supervision improves the model'sperformance significantly and does not require any additional parameters. Thisapproach has the potential to find applications in diverse domains such asmedical analysis and surveillance in which explainability helps to determinesystem fidelity.

Understanding Character Recognition using Visual Explanations Derived from the Human Visual System and Deep Networks