1 code implementation • 21 Jun 2023 • Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Reinhard Koch
While numerous methods exist to solve classification problems within curated datasets, these solutions often fall short in biomedical applications due to the biased or ambiguous nature of the data.
1 code implementation • 22 May 2023 • Lars Schmarje, Vasco Grossmann, Tim Michels, Jakob Nazarenus, Monty Santarossa, Claudius Zelenka, Reinhard Koch
High-quality data is crucial for the success of machine learning, but labeling large datasets is often a time-consuming and costly process.
no code implementations • 22 Jul 2022 • Lars Schmarje, Stefan Reinhold, Timo Damm, Eric Orwoll, Claus-C. Glüer, Reinhard Koch
We show that FORM can correctly predict the 10-year hip fracture risk with a validation AUC of 81. 44 +- 3. 11% / 81. 04 +- 5. 54% (mean +- STD) including additional information like age, BMI, fall history and health background across a 5-fold cross validation on the X-ray and CT cohort, respectively.
no code implementations • 13 Jul 2022 • Vasco Grossmann, Lars Schmarje, Reinhard Koch
High-quality data is a key aspect of modern machine learning.
1 code implementation • 13 Jul 2022 • Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Sabine Dippel, Rainer Kiko, Mariusz Oszust, Matti Pastell, Jenny Stracke, Anna Valros, Nina Volkmann, Reinhard Koch
We propose a data-centric image classification benchmark with ten real-world datasets and multiple annotations per image to allow researchers to investigate and quantify the impact of such data quality issues.
1 code implementation • 13 Oct 2021 • Lars Schmarje, Johannes Brünger, Monty Santarossa, Simon-Martin Schröder, Rainer Kiko, Reinhard Koch
We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels.
no code implementations • 13 Oct 2021 • Lars Schmarje, Reinhard Koch
We envision the incorporation of fuzzy labels into Semi-Supervised Learning and give a proof-of-concept of the potential lower costs and higher consistency in the complete development cycle.
no code implementations • 29 Sep 2021 • Lars Schmarje, Monty Santarossa, Simon-Martin Schröder, Claudius Zelenka, Rainer Kiko, Jenny Stracke, Nina Volkmann, Reinhard Koch
Semi-Supervised Learning (SSL) can decrease the required amount of labeled image data and thus the cost for deep learning.
no code implementations • 7 Jul 2021 • Monty Santarossa, Lukas Schneider, Claudius Zelenka, Lars Schmarje, Reinhard Koch, Uwe Franke
Stixels have been successfully applied to a wide range of vision tasks in autonomous driving, recently including instance segmentation.
1 code implementation • 30 Jun 2021 • Lars Schmarje, Monty Santarossa, Simon-Martin Schröder, Claudius Zelenka, Rainer Kiko, Jenny Stracke, Nina Volkmann, Reinhard Koch
In our data-centric approach, we propose a method to relabel such ambiguous labels instead of implementing the handling of this issue in a neural network.
1 code implementation • 3 Dec 2020 • Lars Schmarje, Johannes Brünger, Monty Santarossa, Simon-Martin Schröder, Rainer Kiko, Reinhard Koch
We propose a novel loss to improve the overclustering capability of our framework and show on the common image classification dataset STL-10 that it is faster and has better overclustering performance than previous work.
no code implementations • 20 Feb 2020 • Lars Schmarje, Monty Santarossa, Simon-Martin Schröder, Reinhard Koch
In this survey, we provide an overview of often used ideas and methods in image classification with fewer labels.
1 code implementation • 30 Jul 2019 • Lars Schmarje, Claudius Zelenka, Ulf Geisen, Claus-C. Glüer, Reinhard Koch
Furthermore, we compare a variety of 2D and 3D methods such as classical approaches like Fourier analysis with state-of-the-art deep neural networks for the classification of local fiber orientations.