Using KL-divergence to focus Deep Visual Explanation
By Housam Khalifa Bashier Babiker, Randy Goebel. 2017
12 citations recorded by the source corpus.
We present a method for explaining the image classification predictions of deep convolution neural networks, by highlighting the pixels in the image which influence the final class prediction. Our method requires the identification of a heuristic method to select parameters hypothesized to be most relevant in this prediction, and here we use Kullback-Leibler divergence to provide this focus. Overall, our approach helps in understanding and interpreting deep network predictions and we hope contributes to a foundation for such understanding of deep learning networks. In this brief paper, our experiments evaluate the performance of two popular networks in this context of interpretability.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Andreas Holzinger
- Katharina Holzinger
- Vanessa Buhrmester
- Michael Arens
- David Münch
- Randy Goebel
- Peter Kieseberg
- Freddy Lécué
Citations in the corpus
- Explainable AI: The New 42? (2018, methodology): “There are an arbitrary number of methods to identify differences in learned variable distributions to create such maps; one such is to compute a Kullback-Leibler (KL) divergence gradient, experiments with which are described in [2], and illustrated in (see Fig.”
- Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey (2019, methodology): “They were inspired from CAM and Grad-CAM and tested the explanator to randomly chosen images from the COCO dataset [82], applied to the pre-trained neural network VGG-16 using Kullback Leibler (KL)-divergence [83].”