In this report, we applied integrated gradients to explaining a neural network for diabetic retinopathy detection. The integrated gradient is an attribution method which measures the contributions of input to the quantity of interest. We explored some new ways for applying this method such as explaining intermediate layers, filtering out unimportant units by their attribution value and generating contrary samples. Moreover, the visualization results extend the use of diabetic retinopathy detection model from merely predicting to assisting finding potential lesions.
@article{arxiv.1709.09586,
title = {Case Study: Explaining Diabetic Retinopathy Detection Deep CNNs via Integrated Gradients},
author = {Linyi Li and Matt Fredrikson and Shayak Sen and Anupam Datta},
journal= {arXiv preprint arXiv:1709.09586},
year = {2017}
}
Comments
This report has been withdrawn as it needs co-authors' permission and further verification of conclusions