Bounded logit attention: Learning to explain image classifiers

05/31/2021
by   Thomas Baumhauer, et al.
2

Explainable artificial intelligence is the attempt to elucidate the workings of systems too complex to be directly accessible to human cognition through suitable side-information referred to as "explanations". We present a trainable explanation module for convolutional image classifiers we call bounded logit attention (BLA). The BLA module learns to select a subset of the convolutional feature map for each input instance, which then serves as an explanation for the classifier's prediction. BLA overcomes several limitations of the instancewise feature selection method "learning to explain" (L2X) introduced by Chen et al. (2018): 1) BLA scales to real-world sized image classification problems, and 2) BLA offers a canonical way to learn explanations of variable size. Due to its modularity BLA lends itself to transfer learning setups and can also be employed as a post-hoc add-on to trained classifiers. Beyond explainability, BLA may serve as a general purpose method for differentiable approximation of subset selection. In a user study we find that BLA explanations are preferred over explanations generated by the popular (Grad-)CAM method.

READ FULL TEXT

page 5

page 15

page 16

page 17

page 18

page 19

page 20

page 21

research
01/16/2018

A Human-Grounded Evaluation Benchmark for Local Explanations of Machine Learning

In order for people to be able to trust and take advantage of the result...
research
01/25/2022

Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts

Existing and planned legislation stipulates various obligations to provi...
research
12/12/2022

PERFEX: Classifier Performance Explanations for Trustworthy AI Systems

Explainability of a classification model is crucial when deployed in rea...
research
09/02/2021

Adherence and Constancy in LIME-RS Explanations for Recommendation

Explainable Recommendation has attracted a lot of attention due to a ren...
research
03/06/2013

A Study of Scaling Issues in Bayesian Belief Networks for Ship Classification

The problems associated with scaling involve active and challenging rese...
research
09/13/2021

Towards Better Model Understanding with Path-Sufficient Explanations

Feature based local attribution methods are amongst the most prevalent i...
research
05/29/2017

Contextual Explanation Networks

We introduce contextual explanation networks (CENs)---a class of models ...

Please sign up or login with your details

Forgot password? Click here to reset