19 citations · 39 across the 5 of their papers we have counts for
6 papers · 1 filter
Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
Doruk Oner, Mateusz Koziński, Leonardo Citraro +3
We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aeri…
TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation
Subeesh Vasu, Mateusz Kozinski, Leonardo Citraro +1
Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is…
Joint Segmentation and Path Classification of Curvilinear Structures
Agata Mosinska, Mateusz Kozinski, Pascal Fua
Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinea…
Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation
Mateusz Koziński, Agata Mosinska, Mathieu Salzmann +1
The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, w…
Beyond the Pixel-Wise Loss for Topology-Aware Delineation
Agata Mosinska, Pablo Marquez-Neila, Mateusz Kozinski +1
Delineation of curvilinear structures is an important problem in Computer Vision with multiple practical applications. With the advent of Deep Learning, many current approaches on…
An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
Mateusz Koziński, Loïc Simon, Frédéric Jurie
We propose a method for semi-supervised training of structured-output neural networks. Inspired by the framework of Generative Adversarial Networks (GAN), we train a discriminator…