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 …

Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

Pre-trained vision-language models (eg, CLIP) have shown promising zero-shot
generalization in many downstream tasks with properly designed text prompts. Instead of …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …

Machine learning techniques used in computer-aided medical image analysis usually suffer
from the domain shift problem caused by different distributions between source/reference …

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 …

The emerging paradigm of federated learning (FL) strives to enable collaborative training of
deep models on the network edge without centrally aggregating raw data and hence …

A model must adapt itself to generalize to new and different data during testing. In this
setting of fully test-time adaptation the model has only the test data and its own parameters …

Today's state-of-the-art machine vision models are vulnerable to image corruptions like
blurring or compression artefacts, limiting their performance in many real-world applications …

Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …