Journal article · Conference paper
LayeredCNN: Segmenting Layers with Autoregressive Models
Visual Computing, Department of Applied Mathematics and Computer Science, Technical University of Denmark1
Department of Applied Mathematics and Computer Science, Technical University of Denmark2
Center for Fast Ultrasound Imaging, UltraSound and Biomechanics, Department of Health Technology, Technical University of Denmark3
UltraSound and Biomechanics, Department of Health Technology, Technical University of Denmark4
Statistics and Data Analysis, Department of Applied Mathematics and Computer Science, Technical University of Denmark5
We address a subclass of segmentation problems where the labels of the image are structured in layers. We propose applying autoregressive CNNs which, when given an image and a partial segmentation of layers, complete the segmentation. Initializing the model with a user-provided partial segmentation allows for choosing which layers the model should segment.
Alternatively, the model can produce an automatic initialization, albeit with some performance loss. The model is trained exclusively on synthetic data from our data generation algorithm. It yields impressive performance on the synthetic data and generalizes to real data it has never seen.
Language: | English |
---|---|
Publisher: | UiT The Arctic University of Norway |
Year: | 2022 |
Proceedings: | Northern Lights Deep Learning Workshop 2022 |
Series: | Proceedings of the Northern Lights Deep Learning Workshop |
ISSN: | 27036928 |
Types: | Journal article and Conference paper |
DOI: | 10.7557/18.6254 |
ORCIDs: | Jensen, Patrick Møller , Hannemose, Morten Rieger , Dahl, Anders Bjorholm , Dahl, Vedrana Andersen and Christensen, Jakob Lønborg |