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 models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

Forgetting refers to the loss or deterioration of previously acquired information or knowledge.
While the existing surveys on forgetting have primarily focused on continual learning …

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on
source data when tested on shifted target data. Most methods update the source model by …

This paper presents a simple yet effective approach that improves continual test-time
adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge …

Test-time adaptation (TTA) methods, which generally rely on the model's predictions (eg,
entropy minimization) to adapt the source pretrained model to the unlabeled target domain …

Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the
robustness challenge under distribution shifts. However, the lack of consistent settings and …

Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-
resolution (HR) using paired HR-LR training images. Conventional SR methods typically …

Generalizing deep learning models to unknown target domain distribution with low latency
has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches …

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 …