Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging

Deep neural networks exhibit limited generalizability across images with different entangled domain features and categorical features. Learning generalizable features that can form universal categorical decision boundaries across domains is an interesting and difficult challenge. This problem occurs...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE Trans Med Imaging
Hlavní autoři: Meng, Qingjie, Matthew, Jacqueline, Zimmer, Veronika A., Gomez, Alberto, Lloyd, David F.A., Rueckert, Daniel, Kainz, Bernhard
Médium: Artigo
Jazyk:Inglês
Vydáno: 2021
Témata:
Article
On-line přístup:https://ncbi.nlm.nih.gov/pmc/articles/PMC7116845/
https://ncbi.nlm.nih.gov/pubmed/33141662
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1109/TMI.2020.3035424
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Podobné jednotky