Compact and efficient deep neural networks for ubiquitous computer vision

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

Project Details


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.
Short titleCoEfNet/Kannala
Effective start/end date01/09/201731/08/2021


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.