skip to main content
Idioma:

GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images

Aadhithya Sankar ; Keicher, Matthias ; Eisawy, Rami ; Parida, Abhijeet ; Pfister, Franz ; Kim, Seong Tae ; Navab, Nassir

arXiv.org, 2021-03

Ithaca: Cornell University Library, arXiv.org

Texto completo disponível

Citações Citado por
  • Título:
    GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images
  • Autor: Aadhithya Sankar ; Keicher, Matthias ; Eisawy, Rami ; Parida, Abhijeet ; Pfister, Franz ; Kim, Seong Tae ; Navab, Nassir
  • Assuntos: Computer Science - Computer Vision and Pattern Recognition ; Medical imaging ; Representations
  • É parte de: arXiv.org, 2021-03
  • Descrição: Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models that require a large number of labelled or unlabelled data. Recently, flow-based generative models have been proposed to generate realistic images by directly modeling the data distribution with invertible functions. In this work, we propose a new flow-based generative model framework, named GLOWin, that is end-to-end invertible and able to learn disentangled representations. Feature disentanglement is achieved by factorizing the latent space into components such that each component learns the representation for one generative factor. Comprehensive experiments have been conducted to evaluate the proposed method on a public brain tumor MR dataset. Quantitative and qualitative results suggest that the proposed method is effective in disentangling the features from complex medical images.
  • Editor: Ithaca: Cornell University Library, arXiv.org
  • Idioma: Inglês
Links
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.