1 code implementation • 21 Jun 2023 • Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Johannes Brünger, Reinhard Koch
In the field of image classification, existing methods often struggle with biased or ambiguous data, a prevalent issue in real-world scenarios.
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.