A New Method to Visualize Deep Neural Networks

TL;DR

This paper introduces a novel visualization technique for deep neural networks that highlights evidence supporting or opposing specific class decisions, enhancing interpretability especially in critical fields like medicine.

Contribution

The proposed method overcomes limitations of previous visualization techniques, providing clearer insights into neural network decision processes on complex datasets like ImageNet.

Findings

Effective visualization of neural network responses on ImageNet

Highlights evidence for and against class decisions

Improves understanding of convolutional network behavior

Abstract

We present a method for visualising the response of a deep neural network to a specific input. For image data for instance our method will highlight areas that provide evidence in favor of, and against choosing a certain class. The method overcomes several shortcomings of previous methods and provides great additional insight into the decision making process of convolutional networks, which is important both to improve models and to accelerate the adoption of such methods in e.g. medicine. In experiments on ImageNet data, we illustrate how the method works and can be applied in different ways to understand deep neural nets.