NC-TTT: A Noise Constrastive Approach for Test-Time Training

D Osowiechi, GAV Hakim, M Noori… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …

Beyond Model Adaptation at Test Time: A Survey

Z Xiao, CGM Snoek - arXiv preprint arXiv:2411.03687, 2024 - arxiv.org
Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

CLIPArTT: Light-weight Adaptation of CLIP to New Domains at Test Time

GAV Hakim, D Osowiechi, M Noori… - arXiv preprint arXiv …, 2024 - arxiv.org
Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable
adaptability across zero-shot classification tasks without additional training. However, their …

ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training

M Colussi, S Mascetti, J Dolz, C Desrosiers - arXiv preprint arXiv …, 2024 - arxiv.org
The remarkable progress in deep learning (DL) showcases outstanding results in various
computer vision tasks. However, adaptation to real-time variations in data distributions …

Test-time Adaptation for Regression by Subspace Alignment

K Adachi, S Yamaguchi, A Kumagai… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

WATT: Weight Average Test-Time Adaption of CLIP

D Osowiechi, M Noori, GAV Hakim… - arXiv preprint arXiv …, 2024 - arxiv.org
Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance
for zero-shot image classification, yet their generalization capability may still be seriously …

MITIGATING DATA SCARCITY CHALLENGES IN MEDICAL IMAGING ANALYSIS: ADVANCED LEARNING APPROACHES WITH EMPHASIS ON HEMOPHILIC …

M Colussi - 2024 - air.unimi.it
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 …

Learning Task Relations for Test-Time Training

W Jeong, J Cho, Y Yoon, KJ Yoon - openreview.net
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 …

[PDF][PDF] NC-TTT: A Noise Constrastive Approach for Test-Time Training-Supplementary Material

D Osowiechi, GAV Hakim, M Noori, M Cheraghalikhani… - openaccess.thecvf.com
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 …

[PDF][PDF] Refining Pseudo Labels for Robust Test Time Adaptation

HGSJH Jo, C Jung - vizwiz.cs.colorado.edu
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 …