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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The expansion of explainable artificial intelligence as a field of researchhas generated numerous methods of visualizing and understanding the black boxof a machine learning model. Attribution maps are generally used to highlightthe parts of the input image that influence the model to make a specificdecision. On the other hand, the robustness of machine learning models tonatural noise and adversarial attacks is also being actively explored. Thispaper focuses on evaluating methods of attribution mapping to find whetherrobust neural networks are more explainable. We explore this problem within theapplication of classification for medical imaging. Explainability research isat an impasse. There are many methods of attribution mapping, but no currentconsensus on how to evaluate them and determine the ones that are the best. Ourexperiments on multiple datasets (natural and medical imaging) and variousattribution methods reveal that two popular evaluation metrics, Deletion andInsertion, have inherent limitations and yield contradictory results. Wepropose a new explainability faithfulness metric (called EvalAttAI) thataddresses the limitations of prior metrics. Using our novel evaluation, wefound that Bayesian deep neural networks using the Variational DensityPropagation technique were consistently more explainable when used with thebest performing attribution method, the Vanilla Gradient. However, in general,various types of robust neural networks may not be more explainable, despitethese models producing more visually plausible attribution maps.

EvalAttAI: A Holistic Approach to Evaluating Attribution Maps in Robust and Non-Robust Models