Attentional bottleneck: Towards an interpretable deep driving network

Jinkyu Kim, Mayank Bansal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and interpretable attention maps (e.g. focusing only on specific vehicles in the scene), but it adds this transparency at no cost to model accuracy. In fact, we find slight improvements in accuracy when applying Attentional Bottleneck to the ChauffeurNet model in comparison to a traditional visual attention model that degrades accuracy.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PublisherIEEE Computer Society
Pages1310-1313
Number of pages4
ISBN (Electronic)9781728193601
DOIs
Publication statusPublished - 2020 Jun
Externally publishedYes
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, United States
Duration: 2020 Jun 142020 Jun 19

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2020-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Country/TerritoryUnited States
CityVirtual, Online
Period20/6/1420/6/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Attentional bottleneck: Towards an interpretable deep driving network'. Together they form a unique fingerprint.

Cite this