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 …

A fascinating hypothesis is that human and animal intelligence could be explained by a few
principles (rather than an encyclopaedic list of heuristics). If that hypothesis was correct, we …

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 …

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 …

This paper presents a new algorithm for domain generalization (DG),\textit {test-time
template adjuster (T3A)}, aiming to robustify a model to unknown distribution shift. Unlike …

Test-time training (TTT) through self-supervised learning (SSL) is an emerging paradigm to
tackle distributional shifts. Despite encouraging results, it remains unclear when 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 …

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 …

Robustness to distribution shifts is critical for deploying machine learning models in the real
world. Despite this necessity, there has been little work in defining the underlying …