Label-efficient domain generalization via collaborative exploration and generalization
Considerable progress has been made in domain generalization (DG) which aims to learn a
generalizable model from multiple well-annotated source domains to unknown target …
generalizable model from multiple well-annotated source domains to unknown target …
Improving pseudo labels with intra-class similarity for unsupervised domain adaptation
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source
domain to a different but related fully-unlabeled target domain. To address the problem of …
domain to a different but related fully-unlabeled target domain. To address the problem of …
Multi-source collaborative contrastive learning for decentralized domain adaptation
Unsupervised multi-source domain adaptation aims to obtain a model working well on the
unlabeled target domain by reducing the domain gap between the labeled source domains …
unlabeled target domain by reducing the domain gap between the labeled source domains …
Joint bi-adversarial learning for unsupervised domain adaptation
Q Tian, J Zhou, Y Chu - Knowledge-Based Systems, 2022 - Elsevier
An important challenge of unsupervised domain adaptation (UDA) is how to sufficiently
utilize the structure and information of the data distribution, so as to exploit the source …
utilize the structure and information of the data distribution, so as to exploit the source …
Making the best of both worlds: A domain-oriented transformer for unsupervised domain adaptation
Extensive studies on Unsupervised Domain Adaptation (UDA) have propelled the
deployment of deep learning from limited experimental datasets into real-world …
deployment of deep learning from limited experimental datasets into real-world …
Self-Training with Label-Feature-Consistency for Domain Adaptation
Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant
representations to address the domain shift. Recently, self-training has been used in UDA …
representations to address the domain shift. Recently, self-training has been used in UDA …
Contrasting augmented features for domain adaptation with limited target domain data
Abstract Domain adaptation aims to alleviate distribution gaps between source and target
domains. However, when the available target domain data are scarce for training, learning …
domains. However, when the available target domain data are scarce for training, learning …
Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
Cross-corpus speech emotion recognition (SER) seeks to generalize the ability of inferring
speech emotion from a well-labeled corpus to an unlabeled one, which is a rather …
speech emotion from a well-labeled corpus to an unlabeled one, which is a rather …
Progressive Contrastive Label Optimization for Source-Free Universal 3D Model Retrieval
Unsupervised Cross-Domain 3D Model Retrieval (UCD3DMR) has emerged as an effective
tool for managing 3D model data recently. However, existing UCD3DMR algorithms typically …
tool for managing 3D model data recently. However, existing UCD3DMR algorithms typically …
Jacobian norm for unsupervised source-free domain adaptation
Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge
from a well-trained source model to a related but unlabeled target domain. In such a …
from a well-trained source model to a related but unlabeled target domain. In such a …