Personne

Mateusz Kozinski

Cette personne n’est plus à l’EPFL

Publications associées (9)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Enforcing Connectivity of 3D Linear Structures Using Their 2D Projections

Pascal Fua, Doruk Oner, Mateusz Kozinski, Hussein Fadl Hassan Hassan Osman

Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural networks trained by minimizing voxel-wise loss functions that do not capture t ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

Pascal Fua, Doruk Oner, Mateusz Kozinski, Leonardo Citraro

We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aerial images. The main idea behind our loss is to express the connectivity of r ...

2021

, ,

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 curvilinear network. Most existing delineation approaches first perform binary segment ...

2020

, , ,

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, we show that we can train a Deep Net to perform 3D volumetric delineation giv ...

ELSEVIER2020

, , ,

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 usually trained by minimizing pixel-wise losses, which is less than ideal t ...

2020

Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images

Pascal Fua, Mateusz Kozinski, Leonardo Citraro

Existing connectivity-oriented performance measures rank road delineation algorithms inconsistently, which makes it difficult to decide which one is best for a given application. We show that these inconsistencies stem from design flaws that make the metri ...

2020

Joint Segmentation and Path Classification of Curvilinear Structures

Pascal Fua, Agata Justyna Mosinska, Mateusz Kozinski

2019

Beyond the Pixel-Wise Loss for Topology-Aware Delineation

Pascal Fua, Pablo Marquez Neila, Agata Justyna Mosinska, Mateusz Kozinski

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 automatic delineation have focused on finding more powerful deep architectur ...

2018

Learning to Segment 3D Linear Structures Using Only 2D Annotations

Pascal Fua, Mathieu Salzmann, Agata Justyna Mosinska, Mateusz Kozinski

We propose a loss function for training a Deep Neural Network (DNN) to segment volumetric data, that accommodates ground truth annotations of 2D projections of the training volumes, instead of annotations of the 3D volumes themselves. In consequence, we si ...

SPRINGER INTERNATIONAL PUBLISHING AG2018