Casting a bait for offline and online source-free domain adaptation
We address the source-free domain adaptation (SFDA) problem, where only the source
model is available during adaptation to the target domain. We consider two settings: the …
model is available during adaptation to the target domain. We consider two settings: the …
Improving diversity and discriminability based implicit contrastive learning for unsupervised domain adaptation
H Xu, C Shi, WZ Fan, Z Chen - Applied Intelligence, 2024 - Springer
In unsupervised domain adaptation (UDA), knowledge is transferred from label-rich source
domains to relevant but unlabeled target domains. Current most popular state-of-the-art …
domains to relevant but unlabeled target domains. Current most popular state-of-the-art …
Style Consistency Unsupervised Domain Adaptation Medical Image Segmentation
L Chen, Y Bian, J Zeng, Q Meng, W Zhu… - … on Image Processing, 2024 - ieeexplore.ieee.org
Unsupervised domain adaptation medical image segmentation is aimed to segment
unlabeled target domain images with labeled source domain images. However, different …
unlabeled target domain images with labeled source domain images. However, different …
Prototype learning for adversarial domain adaptation
Adversarial learning has been widely used in recent years to address the issue of domain
shift in domain adaptation. However, this approach focuses on global cross-domain …
shift in domain adaptation. However, this approach focuses on global cross-domain …
Video Generalized Semantic Segmentation via Non-Salient Feature Reasoning and Consistency
Video semantic segmentation is beneficial for dynamic scene processing in real-world
environments, and achieves superior performance on independent and identically …
environments, and achieves superior performance on independent and identically …
WCAL: Weighted and center-aware adaptation learning for partial domain adaptation
C Zhang, C Hu, J Xie, H Wu, J Zhang - Engineering Applications of Artificial …, 2024 - Elsevier
Partial domain adaptation, which aims to transfer knowledge from a source domain with rich
labels to a unlabeled target domain where target class space is a subspace of source class …
labels to a unlabeled target domain where target class space is a subspace of source class …
Towards Discriminative Class-Aware Domain Alignment via Coding Rate Reduction for Unsupervised Adversarial Domain Adaptation
J Wu, Y Fang - Symmetry, 2024 - search.proquest.com
Unsupervised domain adaptation (UDA) methods, based on adversarial learning, employ
the means of implicit global and class-aware domain alignment to learn the symmetry …
the means of implicit global and class-aware domain alignment to learn the symmetry …
Adaptive Sharpness-Aware Minimization for Adversarial Domain Generalization
T Xie, T Li, R Wu - IEEE Transactions on Computational Social …, 2024 - ieeexplore.ieee.org
To obtain invariant representations, domain-adversarial training has been widely employed,
and it is also frequently used for a variety of domain generalization (DG) tasks. For …
and it is also frequently used for a variety of domain generalization (DG) tasks. For …
A Fourier Transform Framework for Domain Adaptation
L Luo, B Xu, Q Zhang, C Lian, J Luo - Chinese Conference on Pattern …, 2024 - Springer
By utilizing unsupervised domain adaptation (UDA), knowledge can be transferred from a
label-rich source domain to a target domain that contains relevant information but lacks …
label-rich source domain to a target domain that contains relevant information but lacks …
DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection
Z Zhang, J Li, Z Wu, J Shen, J Xu - arXiv preprint arXiv:2407.13147, 2024 - arxiv.org
In recent years, current mainstream feature masking distillation methods mainly function by
reconstructing selectively masked regions of a student network from the feature maps of a …
reconstructing selectively masked regions of a student network from the feature maps of a …