arxivst stuff from arxiv that you should probably bookmark

Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks

Abstract · Apr 13, 2017 13:44 ·

dominant heatmaps clear dnns enhanced making response attentive decision cs-cv cs-ai cs-lg cs-mm

Arxiv Abstract

  • Devinder Kumar
  • Alexander Wong
  • Graham W. Taylor

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand the decisions made by deep neural networks (DNNs) given a specific input. CLEAR facilitates the visualization of attentive regions and levels of interest of DNNs during the decision-making process. It also enables the visualization of the most dominant classes associated with these attentive regions of interest. As such, CLEAR can mitigate some of the shortcomings of heatmap-based methods associated with decision ambiguity, and allows for better insights into the decision-making process of DNNs. Quantitative and qualitative experiments across three different datasets demonstrate the efficacy of CLEAR for gaining a better understanding of the inner workings of DNNs during the decision-making process.

Read the paper (pdf) »