Abstract Machine-learning models for medical tasks can match or surpass the performance
of clinical experts. However, in settings differing from those of the training dataset, the …

Self-supervised pretraining followed by supervised fine-tuning has seen success in image
recognition, especially when labeled examples are scarce, but has received limited attention …

In federated learning, a central server coordinates the training of a single model on a
massively distributed network of devices. This setting can be naturally extended to a multi …

Transfer learning is a standard technique to improve performance on tasks with limited data.
However, for medical imaging, the value of transfer learning is less clear. This is likely due to …

Traditionally, distillation has been used to train a student model to emulate the input/output
functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the …

It has been demonstrated that deep neural networks outperform traditional machine
learning. However, deep networks lack generalisability, that is, they will not perform as good …

Today's generative models are capable of synthesizing high-fidelity images, but each model
specializes on a specific target domain. This raises the need for model merging: combining …

Personalisierung ist ein aktuelles Thema im Bereich der Online-Lehre. Lernende sind
divers, sie haben unterschiedliche Vorkenntnisse, adressieren verschiedene Lernziele und …

This paper proposes a step toward obtaining general models of knowledge for facial
analysis, by addressing the question of multi-source transfer learning. More precisely, the …

The deep learning-based analysis of medical images suffers from data scarcity because of
high annotation costs and privacy concerns. Researchers in this domain have used transfer …