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 …

This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing
on effectively adapting machine learning models to distributionally different target data upon …

Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and
inference in test data streams with domain shifts from the source. Current methods …

Entropy minimization (EM) is frequently used to increase the accuracy of classification
models when they're faced with new data at test time. EM is a self-supervised learning …

Continual test-time domain adaptation (CTTA) aims to adapt the source pre-trained model to
a continually changing target domain without additional data acquisition or labeling costs …

Deep neural networks (DNNs) have revolutionized tasks such as image classification and
speech recognition but often falter when training and test data diverge in distribution …

We present a novel approach for test-time adaptation via online self-training, consisting of
two components. First, we introduce a statistical framework that detects distribution shifts in …

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the
target domain during inference. One popular approach involves fine-tuning model with cross …

Providing a promising pathway to link the human brain with external devices, Brain-
Computer Interfaces (BCIs) have seen notable advancements in decoding capabilities …

Current test-time adaptation (TTA) approaches aim to adapt a machine learning model to
environments that change continuously. Yet, it is unclear whether TTA methods can maintain …