14 citations · 19 across the 6 of their papers we have counts for
6 papers
Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer
Robert A. Marsden, Felix Wiewel, Mario Döbler +2
In recent years, there has been tremendous progress in the field of semantic segmentation. However, one remaining challenging problem is that segmentation models do not generalize…
TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision
Alexander Bartler, Florian Bender, Felix Wiewel +1
Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly.…
Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows
Nico Reick, Felix Wiewel, Alexander Bartler +1
One major drawback of state-of-the-art artificial intelligence is its lack of explainability. One approach to solve the problem is taking causality into account. Causal mechanisms…
MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption
Alexander Bartler, Andre Bühler, Felix Wiewel +2
An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training.…
Condensed Composite Memory Continual Learning
Felix Wiewel, Bin Yang
Deep Neural Networks (DNNs) suffer from a rapid decrease in performance when trained on a sequence of tasks where only data of the most recent task is available. This phenomenon, k…
Localizing Catastrophic Forgetting in Neural Networks
Felix Wiewel, Bin Yang
Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited…