Learning decision trees recurrently through communication

Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

1 Citation (Scopus)

Abstract

Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn iterative binary sub-decisions, inducing sparsity and transparency in the decision making process. The key aspect of our model is its ability to build a decision tree whose structure is encoded into the memory representation of a Recurrent Neural Network jointly learned by two models communicating through message passing. In addition, our model assigns a semantic meaning to each decision in the form of binary attributes, providing concise, semantic and relevant rationalizations to the user. On three benchmark image classification datasets, including the large-scale ImageNet, our model generates human interpretable binary decision sequences explaining the predictions of the network while maintaining state-of-the-art accuracy.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PublisherIEEE computer society
Pages13513-13522
Number of pages10
ISBN (Electronic)9781665445092
ISBN (Print)9781665445108
DOIs
Publication statusPublished - 13 Nov 2021
Event2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States
Duration: 19 Jun 202125 Jun 2021

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Conference2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Country/TerritoryUnited States
CityVirtual, Online
Period19/06/2125/06/21

Fingerprint

Dive into the research topics of 'Learning decision trees recurrently through communication'. Together they form a unique fingerprint.

Cite this