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

Gaining insight into how deep convolutional neural network models performimage classification and how to explain their outputs have been a concern tocomputer vision researchers and decision makers. These deep models are oftenreferred to as black box due to low comprehension of their internal workings.As an effort to developing explainable deep learning models, several methodshave been proposed such as finding gradients of class output with respect toinput image (sensitivity maps), class activation map (CAM), and Gradient basedClass Activation Maps (Grad-CAM). These methods under perform when localizingmultiple occurrences of the same class and do not work for all CNNs. Inaddition, Grad-CAM does not capture the entire object in completeness when usedon single object images, this affect performance on recognition tasks. With theintention to create an enhanced visual explanation in terms of visualsharpness, object localization and explaining multiple occurrences of objectsin a single image, we present Smooth Grad-CAM++ \footnote{Simple demo:http://35.238.22.135:5000/}, a technique that combines methods from two otherrecent techniques---SMOOTHGRAD and Grad-CAM++. Our Smooth Grad-CAM++ techniqueprovides the capability of either visualizing a layer, subset of feature maps,or subset of neurons within a feature map at each instance at the inferencelevel (model prediction process). After experimenting with few images, SmoothGrad-CAM++ produced more visually sharp maps with better localization ofobjects in the given input images when compared with other methods.

Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models