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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

As an emerging field in Machine Learning, Explainable AI (XAI) has beenoffering remarkable performance in interpreting the decisions made byConvolutional Neural Networks (CNNs). To achieve visual explanations for CNNs,methods based on class activation mapping and randomized input sampling havegained great popularity. However, the attribution methods based on thesetechniques provide lower resolution and blurry explanation maps that limittheir explanation power. To circumvent this issue, visualization based onvarious layers is sought. In this work, we collect visualization maps frommultiple layers of the model based on an attribution-based input samplingtechnique and aggregate them to reach a fine-grained and complete explanation.We also propose a layer selection strategy that applies to the whole family ofCNN-based models, based on which our extraction framework is applied tovisualize the last layers of each convolutional block of the model. Moreover,we perform an empirical analysis of the efficacy of derived lower-levelinformation to enhance the represented attributions. Comprehensive experimentsconducted on shallow and deep models trained on natural and industrialdatasets, using both ground-truth and model-truth based evaluation metricsvalidate our proposed algorithm by meeting or outperforming thestate-of-the-art methods in terms of explanation ability and visual quality,demonstrating that our method shows stability regardless of the size of objectsor instances to be explained.

Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation