TY - GEN
T1 - LayeredCNN: Segmenting Layers with Autoregressive Models
AU - Christensen, Jakob Lønborg
AU - Jensen, Patrick Møller
AU - Hannemose, Morten Rieger
AU - Dahl, Anders Bjorholm
AU - Dahl, Vedrana Andersen
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Segmentation
KW - Deep Learning
KW - Autoregressive
KW - Convolutional Neural Network
U2 - 10.7557/18.6254
DO - 10.7557/18.6254
M3 - Article in proceedings
T3 - Proceedings of the Northern Lights Deep Learning Workshop
BT - Proceedings of the Northern Lights Deep Learning Workshop
T2 - Northern Lights Deep Learning Workshop 2022
Y2 - 10 January 2022 through 12 January 2022
ER -