Segment Integrated Gradients: Better attributions through regions

06/06/2019
by   Andrei Kapishnikov, et al.
0

Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, Segment-Integrated Gradients (SIG), that builds upon integrated gradients (Sundararajan et al. 2017), 2) introduce evaluation methods for empirically assessing the quality of image-based saliency maps (Performance Information Curves (PICs)), and 3) contribute an axiom-based sanity check for attribution methods. Through empirical experiments and example results, we show that SIG produces better results than other saliency methods for common models and the ImageNet dataset.

READ FULL TEXT

page 2

page 3

page 5

page 6

page 7

page 8

page 10

page 11

research
04/22/2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Integrated gradients as an attribution method for deep neural network mo...
research
06/14/2022

Attributions Beyond Neural Networks: The Linear Program Case

Linear Programs (LPs) have been one of the building blocks in machine le...
research
06/17/2021

Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

Integrated Gradients (IG) is a commonly used feature attribution method ...
research
10/19/2019

NormGrad: Finding the Pixels that Matter for Training

The different families of saliency methods, either based on contrastive ...
research
10/23/2020

Investigating Saturation Effects in Integrated Gradients

Integrated Gradients has become a popular method for post-hoc model inte...
research
06/27/2021

Crowdsourcing Evaluation of Saliency-based XAI Methods

Understanding the reasons behind the predictions made by deep neural net...
research
09/04/2019

Generalized Integrated Gradients: A practical method for explaining diverse ensembles

We introduce Generalized Integrated Gradients (GIG), a formal extension ...

Please sign up or login with your details

Forgot password? Click here to reset