# Patchnet: Interpretable Neural Networks for Image Classification

Source: [Patchnet: Interpretable Neural Networks for Image Classification](<https://www.sota2.com/research/paper/68fa651f1e209131cea088d8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:19:52.933Z

Authors: Adityanarayanan Radhakrishnan, Charles Durham, Ali Soylemezoglu, Caroline Uhler

Published: 2017-05-23T05:18:14.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1705.08078>)

[PDF](<https://arxiv.org/pdf/1705.08078.pdf>)