Interpretable Explanations of Black Boxes by Meaningful Perturbation

As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been dev...

Full description

Saved in:

Bibliographic Details
Published in:	Proceedings / IEEE International Conference on Computer Vision pp. 3449 - 3457
Main Authors:	Fong, Ruth C., Vedaldi, Andrea
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2017
Subjects:	Backpropagation Gradient methods Machine learning algorithms Neural networks Perturbation methods Prediction algorithms Visualization
ISSN:	2380-7504
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize where highly complex neural networks "look" in an image for evidence for their predictions. However, these techniques are limited by their heuristic nature and architectural constraints. In this paper, we make two main contributions: First, we propose a general framework for learning different kinds of explanations for any black box algorithm. Second, we specialise the framework to find the part of an image most responsible for a classifier decision. Unlike previous works, our method is model-agnostic and testable because it is grounded in explicit and interpretable image perturbations.
ISSN:	2380-7504
DOI:	10.1109/ICCV.2017.371