Joshua Niemeijer
YOU?
Author Swipe
View article: Realistic Evaluation of Deep Active Learning for Image Classification and Semantic Segmentation
Realistic Evaluation of Deep Active Learning for Image Classification and Semantic Segmentation Open
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tas…
View article: TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification
TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification Open
The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of data annotations, typically requiring the engagement of med…
View article: LNQ Challenge 2023: Learning Mediastinal Lymph Node Segmentation with a\n Probabilistic Lymph Node Atlas
LNQ Challenge 2023: Learning Mediastinal Lymph Node Segmentation with a\n Probabilistic Lymph Node Atlas Open
The evaluation of lymph node metastases plays a crucial role in achieving\nprecise cancer staging, influencing subsequent decisions regarding treatment\noptions. Lymph node detection poses challenges due to the presence of unclear\nboundar…
View article: LNQ Challenge 2023: Learning Mediastinal Lymph Node Segmentation with a Probabilistic Lymph Node Atlas
LNQ Challenge 2023: Learning Mediastinal Lymph Node Segmentation with a Probabilistic Lymph Node Atlas Open
The evaluation of lymph node metastases plays a crucial role in achieving precise cancer staging, which in turn influences subsequent decisions regarding treatment options. The detection of lymph nodes poses challenges due to the presence …
View article: Abstract: Reducing Domain Shift in Deep Learning for OCT Segmentation using Image Manipulations
Abstract: Reducing Domain Shift in Deep Learning for OCT Segmentation using Image Manipulations Open
View article: Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation
Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation Open
When models, e.g., for semantic segmentation, are applied to images that are vastly different from training data, the performance will drop significantly. Domain adaptation methods try to overcome this issue, but need samples from the targ…
View article: Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving Open
Deep neural networks (DNNs) have proven their capabilities in many areas in the past years, such as robotics, or automated driving, enabling technological breakthroughs. DNNs play a significant role in environment perception for the challe…
View article: Best Practices in Active Learning for Semantic Segmentation
Best Practices in Active Learning for Semantic Segmentation Open
Active learning is particularly of interest for semantic segmentation, where annotations are costly. Previous academic studies focused on datasets that are already very diverse and where the model is trained in a supervised manner with a l…
View article: Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving Open
Deep neural networks (DNNs) have proven their capabilities in the past years and play a significant role in environment perception for the challenging application of automated driving. They are employed for tasks such as detection, semanti…
View article: Traffic Safety at German Roundabouts—A Replication Study
Traffic Safety at German Roundabouts—A Replication Study Open
Roundabouts are well-known for their ability to improve upon traffic safety, especially for motorized traffic. An in-depth analysis on this topic is known from previous work. It was found that different types of roundabouts have different …
View article: A System for Image-Based Non-Line-Of-Sight Detection Using Convolutional Neural Networks
A System for Image-Based Non-Line-Of-Sight Detection Using Convolutional Neural Networks Open
The ERSAT GGC project introduces the concept of virtual balises for train localization, which avoids investment and maintenance costs of physical balises. Since this concept relies on the matching of train positions to balise positions sto…
View article: Semantische Instanzsegmentierung basierend auf Deep Learning im Kontext des automatisierten Fahrens
Semantische Instanzsegmentierung basierend auf Deep Learning im Kontext des automatisierten Fahrens Open
Die Grundlage, auf der das Selbstfahrende Auto Aktionen plant, bildet ein umfassendes Modell der umgebenden Szene. Eine der Hauptinformationsquellen fur semantische Informationen uber die umgebende Szene sind Kamerabilder. In dieser Arbeit…
View article: A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car
A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car Open
This paper tackles the challenge of scene understanding in context of automated driving. To react properly to the conditions given by the surrounding scene, the car has to understand it’s environment. Further the real time capability of a …