Patchnet: Interpretable Neural Networks for Image Classification
This work addresses the need for interpretability in sensitive domains like healthcare, though it is incremental as it builds on existing methods for feature visualization.
The authors tackled the problem of making neural networks interpretable for image classification by introducing PatchNet, which identifies class-indicative features through a tradeoff between restricting global context and classification error, and demonstrated its effectiveness by achieving competitive performance on the ISBI-ISIC 2017 melanoma classification challenge.
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.