Compact and efficient deep neural networks for ubiquitous computer vision

  • Kannala, Juho (Principal investigator)
  • Ylioinas, Juha (Project Member)
  • Laskar, Zakaria (Project Member)
  • Shershebnev, Aleksandr (Project Member)
  • Tigunova, Anna (Project Member)
  • Wang, Shuzhe (Project Member)
  • Zhao, Yi (Project Member)
  • Verma, Vikas (Project Member)

Project Details

Description

Computer vision has progressed rapidly in many fronts thanks to the adoption of deep neural networks. The large-scale deployment of deep neural network based solutions has however been hindered by computational challenges, which limit their portability to mobile platforms and vehicles. To this extent, the aim of this project is to develop new methodologies for constructing more efficient deep neural networks. The challenge is addressed from two aspects: first, by optimizing existing deep neural networks, and second, by developing efficient neural network architectures from scratch.
StatusFinished
Effective start/end date01/09/201731/08/2021

Collaborative partners

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.
  • Continual Learning for Image-Based Camera Localization

    Wang, S., Laskar, Z., Melekhov, I., Li, X. & Kannala, J., 2022, 2021 International Conference on Computer Vision, ICCV. IEEE, p. 3232-3242 11 p. (IEEE International Conference on Computer Vision).

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

    Open Access
    File
    10 Citations (Scopus)
    76 Downloads (Pure)
  • Novel view synthesis via depth-guided skip connections

    Hou, Y., Solin, A. & Kannala, J., Jan 2021, Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021. IEEE, p. 3118-3127 10 p. (IEEE Winter Conference on Applications of Computer Vision).

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

    Open Access
    7 Citations (Scopus)