"Test-Time Domain Adaptation" · 2 results · Global ETD Search

Results

Showing 1 to 2 of 2 for “"Test-Time Domain Adaptation"”.

Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation

Wang, WeiThe University of Western Ontario2025

… models often fail when deployed in new target domains due to domain shifts. Test-Time Domain Adaptation for Semantic Segmentation (TTDA-Seg) aims to adapt models efficiently during inference without target labels, but existing methods struggle with efficiency (requiring backward optimization) …

uwo Repository record for Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation (opens in a new tab)
Deep Learning Methods for Muscle Analysis From Magnetic Resonance Images

Zhu, Jiayi ; https://orcid.org/0000-0003-3837-7631UNSW, Sydney2024

… generalisability. The fourth study focuses on domain adaptation to overcome the challenge that most deep learning models trained on one specific type of image (source domain) typically do not perform well on other types of images (target domain). To overcome this challenge, a continual …

unsw Repository record for Deep Learning Methods for Muscle Analysis From Magnetic Resonance Images (opens in a new tab)