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

Abstract

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.

Cite

Text

Kumar et al. "Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.215

Markdown

[Kumar et al. "Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/kumar2017cvprw-explaining/) doi:10.1109/CVPRW.2017.215

BibTeX

@inproceedings{kumar2017cvprw-explaining,
  title     = {{Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks}},
  author    = {Kumar, Devinder and Wong, Alexander and Taylor, Graham W.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {1686-1694},
  doi       = {10.1109/CVPRW.2017.215},
  url       = {https://mlanthology.org/cvprw/2017/kumar2017cvprw-explaining/}
}