liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Attentional Masking for Pre-trained Deep Networks
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-5698-5983
2017 (English)In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS17), Institute of Electrical and Electronics Engineers (IEEE), 2017Conference paper, Published paper (Refereed)
Abstract [en]

The ability to direct visual attention is a fundamental skill for seeing robots. Attention comes in two flavours: the gaze direction (overt attention) and attention to a specific part of the current field of view (covert attention), of which the latter is the focus of the present study. Specifically, we study the effects of attentional masking within pre-trained deep neural networks for the purpose of handling ambiguous scenes containing multiple objects. We investigate several variants of attentional masking on partially pre-trained deep neural networks and evaluate the effects on classification performance and sensitivity to attention mask errors in multi-object scenes. We find that a combined scheme consisting of multi-level masking and blending provides the best trade-off between classification accuracy and insensitivity to masking errors. This proposed approach is denoted multilayer continuous-valued convolutional feature masking (MC-CFM). For reasonably accurate masks it can suppress the influence of distracting objects and reach comparable classification performance to unmasked recognition in cases without distractors.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2017.
National Category
Computer Vision and Robotics (Autonomous Systems) Computer Systems
Identifiers
URN: urn:nbn:se:liu:diva-142061OAI: oai:DiVA.org:liu-142061DiVA: diva2:1150792
Conference
The 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017), September 24–28, Vancouver, Canada
Available from: 2017-10-20 Created: 2017-10-20 Last updated: 2017-11-10Bibliographically approved

Open Access in DiVA

No full text

Other links

Link to full text

Authority records BETA

Wallenberg, MarcusForssen, Per-Erik

Search in DiVA

By author/editor
Wallenberg, MarcusForssen, Per-Erik
By organisation
Computer VisionFaculty of Science & Engineering
Computer Vision and Robotics (Autonomous Systems)Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 93 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf