New hierarchy-based segmentation layer: towards automatic marker proposal

  • Gabriel Barbosa da Fonseca PUC Minas / Université Gustave Eiffel
  • Romain Negrel Université Gustave Eiffel
  • Benjamin Perret Université Gustave Eiffel
  • Jean Cousty Université Gustave Eiffel
  • Silvio Jamil F. Guimarães PUC Minas


Image segmentation is an ill-posed problem by definition, as it is not always possible to automatically select which object appearing in an image is the object of interest. To deal with this issue, prior knowledge in the form of human-given markers can be included in the segmentation pipeline. Even though user interaction can drastically improve segmentation results, it is an expensive resource, and finding ways to reduce human effort on an interactive segmentation loop is of great interest. In this work, we propose a new segmentation layer to be used with deep neural networks, which allows us to create and train in an end-to-end fashion a marker creation network. To train the network, we propose a loss function composed of: a segmentation loss using the proposed differentiable segmentation layer; and a set of regularization functions that enforce the desired characteristics on the produced markers. We showed that by using the proposed layer and loss function, we can train the network to automatically generate markers that recover a good segmentation and have desirable shape characteristics. This behavior is observed on the training dataset, as well as on four unseen datasets.
Palavras-chave: Training, Deep learning, Image segmentation, Shape, Pipelines, Proposals, Interactive image segmentation, Automatic marker proposal, Hierarchy based, Segmentation layer
Como Citar

Selecione um Formato
FONSECA, Gabriel Barbosa da; NEGREL, Romain; PERRET, Benjamin; COUSTY, Jean; GUIMARÃES, Silvio Jamil F.. New hierarchy-based segmentation layer: towards automatic marker proposal. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 34. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 .