Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Test-time adaptation provides an effective means of tackling the potential distribution shift
between model training and inference, by dynamically updating the model at test time. This …

While deep neural networks can attain good accuracy on in-distribution test points, many
applications require robustness even in the face of unexpected perturbations in the input …

Test-time adaptation (TTA) has shown to be effective at tackling distribution shifts between
training and testing data by adapting a given model on test samples. However, the online …

Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption
(TTA) continues to adapt the model after deployment. Recently, the area of continual and …

State-of-the-art deepfake detectors perform well in identifying forgeries when they are
evaluated on a test set similar to the training set, but struggle to maintain good performance …

The main challenge in domain generalization (DG) is to handle the distribution shift problem
that lies between the training and test data. Recent studies suggest that test-time training …

Compared to traditional machine learning, deep learning can learn deeper abstract data
representation and understand scattered data properties. It has gained considerable …

Federated learning (FL) is an effective machine learning paradigm where multiple clients
can train models based on heterogeneous data in a decentralized manner without …

Test-time adaptation (TTA) adapts a source model to the distribution shift in testing data
without using any source data. There have been plenty of algorithms concentrated on …