A New Method to Visualize Deep Neural Networks

2016/03/08 by Luisa Zintgraf, Taco Cohen, Zintgraf, Luisa M. +3
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.1603.02518

openalex publication_date 2016/03/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Understanding Neural Networks Through Deep Visualization
• Object Detectors Emerge in Deep Scene CNNs
• ImageNet Large Scale Visual Recognition Challenge
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Related

• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• Efficient Image Evidence Analysis of CNN Classification Results
• Understanding Neural Networks Through Deep Visualization
• NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions
• Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks