White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks

Abstract

In recent years, deep learning has become prevalent to solve applications from multiple domains. Convolutional Neural Networks (CNNs) particularly have demonstrated state of the art performance for the task of image classification. However, the decisions made by these networks are not transparent and cannot be directly interpreted by a human. Several approaches have been proposed to explain to understand the reasoning behind a prediction made by a network. In this paper, we propose a topology of grouping these methods based on their assumptions and implementations. We focus primarily on white box methods that leverage the information of the internal architecture of a network to explain its decision. Given the task of image classification and a trained CNN, this work aims to provide a comprehensive and detailed overview of a set of methods that can be used to create explanation maps for a particular image, that assign an importance score to each pixel of the image based on its contribution to the decision of the network. We also propose a further classification of the white box methods based on their implementations to enable better comparisons and help researchers find methods best suited for different scenarios.

arXiv commentSubmitted to Journal of Electronic Imaging (JEI)

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• Intriguing properties of neural networks
• How transferable are features in deep neural networks?
• Axiomatic Attribution for Deep Networks
• Striving for Simplicity: The All Convolutional Net
• Learning Important Features Through Propagating Activation Differences
• Squeeze-and-Excitation Networks
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Sanity Checks for Saliency Maps
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Distilling a Neural Network Into a Soft Decision Tree
• Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems
• The Shattered Gradients Problem: If resnets are the answer, then what is the question?
• Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
• Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification

Cited by in corpus (1)

• Transfer learning, alternative approaches, and visualization of a convolutional neural network for retrieval of the internuclear distance in a molecule from photoelectron momentum distributions