Transferable Query Selection for Active Domain Adaptation
Unsupervised domain adaptation (UDA) enables transferring knowledge from a related source domain to a fully unlabeled target domain. Despite the significant advances in UDA, the performance gap remains quite large between UDA and supervised learning with fully labeled target data. Active domain adaptation (ADA) mitigates the gap under minimal annotation cost by selecting a small quota of target samples to annotate and incorporating them into training. Due to the domain shift, the query selection criteria of prior active learning methods may be ineffective to select the most informative target samples for annotation. In this paper, we propose Transferable Query Selection (TQS), which selects the most informative samples under domain shift by an ensemble of three new criteria: transferable committee, transferable uncertainty, and transferable domainness. We further develop a randomized selection algorithm to enhance the diversity of the selected samples. Experiments show that TQS remarkably outperforms previous UDA and ADA methods on several domain adaptation datasets. Deeper analyses demonstrate that TQS can select the most informative target samples under the domain shift.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningDiversityDomain AdaptationUnsupervised Domain AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Loss-based Sequential Learning for Active Domain Adaptation
Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but …
DiversityDomain AdaptationLearning Distinctive Margin toward Active Domain Adaptation
Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due t…
Active LearningDomain AdaptationGALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation
Domain Adaptation (DA) provides an effective way to tackle target-domain tasks by leveraging knowledge learned from source domains. Recent studies have extended this paradigm to Multi-Source Domain Adaptation (MSDA), whi…
Domain AdaptationActive LearningDiscriminative Active Learning for Domain Adaptation
Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous works mainly focused on matching the marg…
Active LearningDiversityDomain AdaptationBridge-Based Active Domain Adaptation for Aspect Term Extraction
As a fine-grained task, the annotation cost of aspect term extraction is extremely high. Recent attempts alleviate this issue using domain adaptation that transfers common knowledge across domains. Since most aspect term…
Domain AdaptationTerm Extraction