To Örebro University

oru.seÖrebro University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks
Redwood Center for Theoretical Neuroscience, UC Berkeley, Berkeley, USA.
Université Paris-Saclay, ENS Paris-Saclay, Gif-sur-Yvette, France; Redwood Center for Theoretical Neuroscience, UC Berkeley, Berkeley, USA.
Redwood Center for Theoretical Neuroscience, UC Berkeley, Berkeley, USA.
Örebro University, School of Science and Technology. Intelligent Systems Lab, Research Institutes of Sweden, Kista, Sweden. (Centre for Applied Autonomous Sensor System)ORCID iD: 0000-0002-6032-6155
Show others and affiliations
2024 (English)In: 2024 Neuro Inspired Computational Elements Conference (NICE), IEEE , 2024Conference paper, Published paper (Refereed)
Abstract [en]

We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content. The sparse feature representation is learned from image statistics via convolutional sparse coding, while scene parsing is performed by a resonator network [1]. The integration of sparse coding with the resonator network increases the capacity of distributed representations and reduces collisions in the combinatorial search space during factorization. We find that for this problem the resonator network is capable of fast and accurate vector factorization, and we develop a confidence-based metric that assists in tracking the convergence of the resonator network.

Place, publisher, year, edition, pages
IEEE , 2024.
Keywords [en]
hyperdimensional computing, vector symbolic architectures, sparse coding, resonator networks, visual scene understanding, combinatorial search, vector factorization, computing-in-superposition
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-115360DOI: 10.1109/NICE61972.2024.10549719ISI: 001253426500021Scopus ID: 2-s2.0-85196224848ISBN: 9798350390599 (print)ISBN: 9798350390582 (electronic)OAI: oai:DiVA.org:oru-115360DiVA, id: diva2:1890355
Conference
Neuro Inspired Computational Elements Conference (NICE), La Jolla, CA, USA, April 23-26, 2024
Funder
EU, Horizon 2020, 839179
Note

The work of CJK was supported by the Department of Defense (DoD) through the National Defense Science & Engineering Graduate (NDSEG) Fellowship Program. The work of SM was carried out as part of the ARPE program of ENS Paris-Saclay. The work of DK and BAO was supported in part by Intel's THWAI program. The work of CJK and BAO was supported by the Center for the Co -Design of Cognitive Systems (CoCoSys), one of seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program sponsored by DARPA. DK has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 839179.

Available from: 2024-08-19 Created: 2024-08-19 Last updated: 2024-08-19Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Kleyko, Denis

Search in DiVA

By author/editor
Kleyko, Denis
By organisation
School of Science and Technology
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 127 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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