Search Results for author:
Found 7 papers, 3 papers with code
Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer
In this work, we focus on UDA and additionally address the case of adapting not only to a single domain, but to a sequence of target domains.
TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision
Nowadays, deep neural networks outperform humans in many tasks.
Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows
One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption
By minimizing the self-supervised loss, we learn task-specific model parameters for different tasks.
Condensed Composite Memory Continual Learning
While many recently proposed methods for continual learning use some training examples for rehearsal, their performance strongly depends on the number of stored examples.
Localizing Catastrophic Forgetting in Neural Networks
Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks.
Training Variational Auto Encoders with Discrete Latent Representations using Importance Sampling
In this paper, we propose an easy method to train VAEs with binary or categorically valued latent representations.
