A comprehensive survey on test-time adaptation under distribution shifts
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 …
process that can effectively generalize to test samples, even in the presence of distribution …
Source-free unsupervised domain adaptation: Current research and future directions
In the field of Transfer Learning, Source-Free Unsupervised Domain Adaptation (SFUDA)
emerges as a practical and novel task that enables a pre-trained model to adapt to a new …
emerges as a practical and novel task that enables a pre-trained model to adapt to a new …
Cdtrans: Cross-domain transformer for unsupervised domain adaptation
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled
source domain to a different unlabeled target domain. Most existing UDA methods focus on …
source domain to a different unlabeled target domain. Most existing UDA methods focus on …
Balancing discriminability and transferability for source-free domain adaptation
Conventional domain adaptation (DA) techniques aim to improve domain transferability by
learning domain-invariant representations; while concurrently preserving the task …
learning domain-invariant representations; while concurrently preserving the task …
Dynamic weighted learning for unsupervised domain adaptation
N Xiao, L Zhang - Proceedings of the IEEE/CVF conference …, 2021 - openaccess.thecvf.com
Unsupervised domain adaptation (UDA) aims to improve the classification performance on
an unlabeled target domain by leveraging information from a fully labeled source domain …
an unlabeled target domain by leveraging information from a fully labeled source domain …
Sofa: Source-data-free feature alignment for unsupervised domain adaptation
Applying a trained model on a new scenario may suffer from domain shift. Unsupervised
domain adaptation (UDA) has been proven to be an effective approach to solve the problem …
domain adaptation (UDA) has been proven to be an effective approach to solve the problem …
Source-free adaptation to measurement shift via bottom-up feature restoration
Source-free domain adaptation (SFDA) aims to adapt a model trained on labelled data in a
source domain to unlabelled data in a target domain without access to the source-domain …
source domain to unlabelled data in a target domain without access to the source-domain …
Estimating egocentric 3d human pose in global space
Egocentric 3D human pose estimation using a single fisheye camera has become popular
recently as it allows capturing a wide range of daily activities in unconstrained environments …
recently as it allows capturing a wide range of daily activities in unconstrained environments …
Unsupervised domain adaptation of black-box source models
Unsupervised domain adaptation (UDA) aims to learn models for a target domain of
unlabeled data by transferring knowledge from a labeled source domain. In the traditional …
unlabeled data by transferring knowledge from a labeled source domain. In the traditional …
Balancing transferability and discriminability for unsupervised domain adaptation
J Huang, N Xiao, L Zhang - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) aims to leverage a sufficiently labeled source
domain to classify or represent the fully unlabeled target domain with a different distribution …
domain to classify or represent the fully unlabeled target domain with a different distribution …