no code implementations • ECCV 2020 • Leonardo Citraro, Mateusz Koziński, Pascal Fua
Existing connectivity-oriented performance measures rank road delineation algorithms inconsistently, which makes it difficult to decide which one is best for a given application.
1 code implementation • 6 Dec 2021 • Doruk Oner, Leonardo Citraro, Mateusz Koziński, Pascal Fua
Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks.
no code implementations • 12 Oct 2021 • Doruk Oner, Adélie Garin, Mateusz Koziński, Kathryn Hess, Pascal Fua
Persistent Homology (PH) has been successfully used to train networks to detect curvilinear structures and to improve the topological quality of their results.
1 code implementation • 15 Sep 2020 • Doruk Oner, Mateusz Koziński, Leonardo Citraro, Nathan C. Dadap, Alexandra G. Konings, Pascal Fua
The main idea behind our loss is to express the connectivity of roads, or canals, in terms of disconnections that they create between background regions of the image.
no code implementations • 28 Nov 2019 • Leonardo Citraro, Mateusz Koziński, Pascal Fua
Existing performance measures rank delineation algorithms inconsistently, which makes it difficult to decide which one is best in any given situation.
1 code implementation • 26 Nov 2018 • Mateusz Koziński, Agata Mosinska, Mathieu Salzmann, Pascal Fua
The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis.
no code implementations • 8 Feb 2017 • Mateusz Koziński, Loïc Simon, Frédéric Jurie
We propose a method for semi-supervised training of structured-output neural networks.