LayeredCNN: Segmenting Layers with Autoregressive Models

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

18 Downloads (Orbit)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the Northern Lights Deep Learning Workshop
Number of pages8
Publication date2022
DOIs
Publication statusPublished - 2022
EventNorthern Lights Deep Learning Workshop 2022 - Tromsø, Norway
Duration: 10 Jan 202212 Jan 2022

Conference

ConferenceNorthern Lights Deep Learning Workshop 2022
Country/TerritoryNorway
CityTromsø
Period10/01/202212/01/2022
SeriesProceedings of the Northern Lights Deep Learning Workshop
Volume3
ISSN2703-6928

Keywords

  • Segmentation
  • Deep Learning
  • Autoregressive
  • Convolutional Neural Network

Fingerprint

Dive into the research topics of 'LayeredCNN: Segmenting Layers with Autoregressive Models'. Together they form a unique fingerprint.

Cite this