activity
20172020
most citedAn Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks

19 citations · 39 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20201 cited

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…

cs.CV2020

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…

cs.CV20192 cited

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…

cs.CV2018

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…

cs.CV201717 cited

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…

cs.CV201719 cited

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…