1 code implementation • 26 Nov 2023 • Jann Goschenhofer, Bernd Bischl, Zsolt Kira
Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervision-level model performance.
no code implementations • 17 Feb 2023 • Julian Rodemann, Jann Goschenhofer, Emilio Dorigatti, Thomas Nagler, Thomas Augustin
We derive this selection criterion by proving Bayes optimality of the posterior predictive of pseudo-samples.
1 code implementation • 12 Jan 2023 • Cem Akkus, Luyang Chu, Vladana Djakovic, Steffen Jauch-Walser, Philipp Koch, Giacomo Loss, Christopher Marquardt, Marco Moldovan, Nadja Sauter, Maximilian Schneider, Rickmer Schulte, Karol Urbanczyk, Jann Goschenhofer, Christian Heumann, Rasmus Hvingelby, Daniel Schalk, Matthias Aßenmacher
This book is the result of a seminar in which we reviewed multimodal approaches and attempted to create a solid overview of the field, starting with the current state-of-the-art approaches in the two subfields of Deep Learning individually.
no code implementations • 31 Jan 2022 • Emilio Dorigatti, Jann Goschenhofer, Benjamin Schubert, Mina Rezaei, Bernd Bischl
In this work, we thus propose to tackle the issues of imbalanced datasets and model calibration in a PUL setting through an uncertainty-aware pseudo-labeling procedure (PUUPL): by boosting the signal from the minority class, pseudo-labeling expands the labeled dataset with new samples from the unlabeled set, while explicit uncertainty quantification prevents the emergence of harmful confirmation bias leading to increased predictive performance.
1 code implementation • 6 Feb 2021 • Jann Goschenhofer, Rasmus Hvingelby, David Rügamer, Janek Thomas, Moritz Wagner, Bernd Bischl
Based on these adaptations, we explore the potential of deep semi-supervised learning in the context of time series classification by evaluating our methods on large public time series classification problems with varying amounts of labelled samples.
no code implementations • 15 Nov 2019 • Kamer A. Yuksel, Jann Goschenhofer, Hridya V. Varma, Urban Fietzek, Franz M. J. Pfister
Parkinson's disease (PD) is the second most common neurodegenerative disease worldwide and affects around 1% of the (60+ years old) elderly population in industrial nations.
no code implementations • 24 Apr 2019 • Jann Goschenhofer, Franz MJ Pfister, Kamer Ali Yuksel, Bernd Bischl, Urban Fietzek, Janek Thomas
To solve the problem of limited availability of high quality training data, we propose a transfer learning technique which helps to improve model performance substantially.