Case Study: Explaining Diabetic Retinopathy Detection Deep CNNs via Integrated Gradients

09/27/2017
by   Linyi Li, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

04/22/2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Integrated gradients as an attribution method for deep neural network mo...
09/04/2019

Generalized Integrated Gradients: A practical method for explaining diverse ensembles

We introduce Generalized Integrated Gradients (GIG), a formal extension ...
08/31/2021

Discretized Integrated Gradients for Explaining Language Models

As a prominent attribution-based explanation algorithm, Integrated Gradi...
05/05/2019

Explaining Cybersecurity with Films and the Arts (Extended Abstract)

Explaining Cybersecurity with Films and the Arts...
02/10/2020

Explaining Explanations: Axiomatic Feature Interactions for Deep Networks

Recent work has shown great promise in explaining neural network behavio...
11/21/2018

Compensated Integrated Gradients to Reliably Interpret EEG Classification

Integrated gradients are widely employed to evaluate the contribution of...
04/21/2019

Explaining a prediction in some nonlinear models

In this article we will analyse how to compute the contribution of each ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.