• Bokmål
  • English


Project vision and goals

Project vision and goals

Project vision

The vision of this project is to make a leap forward in the research on deep learning by making these autonomous deep cognitive models useful for image-based applications anywhere – also for applications on non-standard images with sparsely labelled data. The aim is to arrive at generic models and exploit them to solve key big data computer vision challenges in the marine sector.

Project objectives

To fulfil the vision, the project aims to develop cognitive and generic methods that enable autonomous analysis of non-standard, sparsely labelled image data by building on concepts from cross-domain transfer learning, semi-supervised learning and data simulation. More specifically, our main objectives are to:
  1. Develop new cognitive models and methods for sparsely labelled, non-standard image data
  2. Develop methods that provide easy-to-adapt solutions to analyse new non-standard image data
  3. Demonstrate the methodology for big data challenges in the marine sector
The project focuses on aiding the automation of three corner stones in computer vision, classification, localization and segmentation. Achieving this will help innovating the next generation big data services for the marine sector.
Norsk Regnesentral
Postboks 114 Blindern
0314 Oslo
Norsk Regnesentral
Gaustadalleen 23a
Kristen Nygaards hus
0373 Oslo
(+47) 22 85 25 00
Adresse Hvordan komme til NR
Sosiale media Del på sosiale media
Personvernerklæring Personvernerklæring
Postadresse: Norsk Regnesentral, Postboks 114 Blindern, 0314 Oslo
Besøksadresse: Norsk Regnesentral, Gaustadalleen 23a, Kristen Nygaards hus, 0373 Oslo
Tlf: (+47) 22 85 25 00
AdresseHvordan komme til NR