Despite their exceptional performance in vision tasks deep learning models often struggle
when faced with domain shifts during testing. Test-Time Training (TTT) methods have …

Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable
adaptability across zero-shot classification tasks without additional training. However, their …

The remarkable progress in deep learning (DL) showcases outstanding results in various
computer vision tasks. However, adaptation to real-time variations in data distributions …

This paper investigates test-time adaptation (TTA) for regression, where a regression model
pre-trained in a source domain is adapted to an unknown target distribution with unlabeled …

Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance
for zero-shot image classification, yet their generalization capability may still be seriously …

Medical imaging plays a crucial role in hemophilia research and clinical practice, particularly
in assessing joint health and bleeding events. Ultrasound (US) imaging is a fundamental …

Generalizing deep neural networks to unseen target domains presents a major challenge in
real-world deployments. Test-time training (TTT) addresses this is-sue by using an auxiliary …

Figure 1. Test-time accuracy on different layer blocks with different in-distribution standard
deviation. methods as the severity augments, but NC-TTT outperforms the closest …

Test-time adaptation (TTA) addresses challenges related to distribution shift by allowing the
model to adapt to target data during testing without the need for source data. TTA has made …