Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation …
P Zhu, Z Zhu, Y Wang, J Zhang, S Zhao - Pattern Recognition, 2022 - Elsevier
Few-shot learning (FSL) aims at fast adaptation to novel classes with few training samples. Among FSL methods, meta-learning and transfer learning-based methods are the most …
Adversarial domain adaptation has made remarkable in promoting feature transferability, while recent work reveals that there exists an unexpected degradation of feature …
J Zhuo, S Wang, Q Huang - IEEE Transactions on Multimedia, 2022 - ieeexplore.ieee.org
In this paper, we tackle the task of domain adaptation under noisy environments; this is a practical and challenging problem in which the source domain is corrupted with noise in its …
M Meng, Z Wu, T Liang, J Yu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Unsupervised domain adaptation aims to leverage knowledge from a labeled source domain to learn an accurate model in an unlabeled target domain. However, many previous …
S Liu, M Jiang, J Kong - … on Circuits and Systems for Video …, 2022 - ieeexplore.ieee.org
Few-shot action recognition classifies new actions with only few training samples, of which the mainstream methods adopt class means to obtain prototypes as the representations of …
X Ma, J Yuan, Y Chen, R Tong, L Lin - Neurocomputing, 2022 - Elsevier
Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To …
Deep learning is reaching state of the art in many applications. However, the generalization capabilities of the learned networks are limited to the training or source domain. The …
Domain adaptation enables generalized learning in new environments by transferring knowledge from label-rich source domains to label-scarce target domains. As a more …