Scipediacontent: Scipediacontent moved page Draft Content 451223266 to Guidotti et al 2020a

2021-01-21T14:19:25Z

Scipediacontent moved page Draft Content 451223266 to Guidotti et al 2020a

Scipediacontent: Created page with " == Abstract == We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation metho..."

2021-01-21T14:19:21Z

Created page with " == Abstract == We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation metho..."

New page

== Abstract ==

We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation method exploits the latent feature space learned through an adversarial autoencoder. The proposed method first generates exemplar images in the latent feature space and learns a decision tree classifier. Then, it selects and decodes exemplars respecting local decision rules. Finally, it visualizes them in a manner that shows to the user how the exemplars can be modified to either stay within their class, or to become counter-factuals by "morphing" into another class. Since we focus on black box decision systems for image classification, the explanation obtained from the exemplars also provides a saliency map highlighting the areas of the image that contribute to its classification, and areas of the image that push it into another class. We present the results of an experimental evaluation on three datasets and two black box models. Besides providing the most useful and interpretable explanations, we show that the proposed method outperforms existing explainers in terms of fidelity, relevance, coherence, and stability.

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/2002.03746 http://arxiv.org/abs/2002.03746]

* [http://arxiv.org/pdf/2002.03746 http://arxiv.org/pdf/2002.03746]

* [http://link.springer.com/content/pdf/10.1007/978-3-030-46150-8_12 http://link.springer.com/content/pdf/10.1007/978-3-030-46150-8_12],
: [http://dx.doi.org/10.1007/978-3-030-46150-8_12 http://dx.doi.org/10.1007/978-3-030-46150-8_12] under the license http://www.springer.com/tdm

* [https://dblp.uni-trier.de/db/journals/corr/corr2002.html#abs-2002-03746 https://dblp.uni-trier.de/db/journals/corr/corr2002.html#abs-2002-03746],
: [https://arxiv.org/pdf/2002.03746 https://arxiv.org/pdf/2002.03746],
: [https://link.springer.com/chapter/10.1007/978-3-030-46150-8_12 https://link.springer.com/chapter/10.1007/978-3-030-46150-8_12],
: [https://academic.microsoft.com/#/detail/3029534136 https://academic.microsoft.com/#/detail/3029534136]

← Older revision	Revision as of 14:19, 21 January 2021
(No difference)

Guidotti et al 2020a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 451223266 to Guidotti et al 2020a

Scipediacontent: Created page with " == Abstract == We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation metho..."