In this work, we provide a survey of active learning (AL) for its applications in natural language processing (NLP). In addition to a fine-grained categorization of query strategies …
Y Fu, X Zhu, B Li - Knowledge and information systems, 2013 - Springer
Active learning aims to train an accurate prediction model with minimum cost by labeling most informative instances. In this paper, we survey existing works on active learning from …
T Wang, X Zhang, L Yuan… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with …
We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two …
B Fu, Z Cao, J Wang, M Long - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Unsupervised domain adaptation (UDA) enables transferring knowledge from a related source domain to a fully unlabeled target domain. Despite the significant advances in UDA …
S Hanneke, S Kpotufe - Advances in Neural Information …, 2019 - proceedings.neurips.cc
We aim to understand the value of additional labeled or unlabeled target data in transfer learning, for any given amount of source data; this is motivated by practical questions …
X Li, Z Du, J Li, L Zhu, K Lu - Proceedings of the 30th ACM international …, 2022 - dl.acm.org
Unsupervised domain adaptation (UDA) aims at transferring knowledge from one labeled source domain to a related but unlabeled target domain. Recently, active domain adaptation …
Visual domain adaptation aims to seek an effective transferable model for unlabeled target images by benefiting from the well-labeled source images following different distributions …