To main content

Marianne Bakken

Research Scientist/PhD Fellow

Marianne Bakken

Research Scientist/PhD Fellow

Marianne Bakken
Phone: +47 958 98 490
Email:
Department: Smart Sensor Systems
Office: Oslo

Publications and responsibilities

Publication
https://www.sintef.no/en/publications/publication/?pubid=1872165

We introduce a new visualisation technique for CNNs called Principal Feature Visualisation (PFV). It uses a single forward pass of the original network to map principal features from the nal convolutional layer to the original image space as RGB channels. By working on a batch of images we can...

Year 2020
Type Academic article
Publication
https://www.sintef.no/en/publications/publication/?pubid=1687425

We consider the case of robotic bin picking of reflective steel parts, using a structured light 3D camera as a depth imaging device. In this paper, we present a new method for bin picking, based on a dual-resolution convolutional neural network trained entirely in a simulated environment. The dual...

Year 2018
Type Academic chapter/article/Conference paper