Understanding how a complex machine learning model makes a classification decision is essential for its acceptance in sensitive areas such as health care. Towards this end, we present PatchNet, a method that provides the features indicative of each class in an image using a tradeoff between restricting global image context and classification error. We mathematically analyze this tradeoff, demonstrate Patchnet's ability to construct sharp visual heatmap representations of the learned features, and quantitatively compare these features with features selected by domain experts by applying PatchNet to the classification of benign/malignant skin lesions from the ISBI-ISIC 2017 melanoma classification challenge.
@article{arxiv.1705.08078,
title = {Patchnet: Interpretable Neural Networks for Image Classification},
author = {Adityanarayanan Radhakrishnan and Charles Durham and Ali Soylemezoglu and Caroline Uhler},
journal= {arXiv preprint arXiv:1705.08078},
year = {2018}
}
Comments
Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216