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

In recent years, neural networks have continued to flourish, achieving highefficiency in detecting relevant objects in photos or simply recognizing(classifying) these objects - mainly using CNN networks. Current solutions,however, are far from ideal, because it often turns out that network can beeffectively confused with even natural images examples. I suspect that theclassification of an object is strongly influenced by the background pixels onwhich the object is located. In my work, I analyze the above problem using forthis purpose saliency maps created by the LICNN network. They are designed tosuppress the neurons surrounding the examined object and, consequently, reducethe contribution of background pixels to the classifier predictions. Myexperiments on the natural and adversarial images datasets show that, indeed,there is a visible correlation between the background and the wrong-classifiedforeground object. This behavior of the network is not supported by humanexperience, because, for example, we do not confuse the yellow school bus withthe snow plow just because it is on the snowy background.

Reproduction of Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection