# Explainability in CNN Models By Means of Z-Scores

arXiv: https://arxiv.org/abs/2102.05874 · HTML: https://mlsanity.com/paper/2102.05874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 7 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 4 of 4)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Interpreting Deep Visual Representations via Network Dissection](https://mlsanity.com/paper/1711.05611/) (2017)

## Abstract (arXiv)

This paper explores the similarities of output layers in Neural Networks (NNs) with logistic regression to explain importance of inputs by Z-scores. The network analyzed, a network for fusion of Synthetic Aperture Radar (SAR) and Microwave Radiometry (MWR) data, is applied to prediction of arctic sea ice. With the analysis the importance of MWR relative to SAR is found to favor MWR components. Further, as the model represents image features at different scales, the relative importance of these are as well analyzed. The suggested methodology offers a simple and easy framework for analyzing output layer components and can reduce the number of components for further analysis with e.g. common NN visualization methods.