In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect
enough large-scale supervised data to train deep networks. Transfer learning can reuse the …

Multi-source domain adaptation (MDA) aims to transfer knowledge from multiple source
domains to an unlabeled target domain. MDA is a challenging task due to the severe …

Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source
domain to an unlabeled target domain. Existing UDA-based semantic segmentation …

Learning methods are challenged when there is not enough labelled data. It gets worse
when the existing learning data have different distributions in different domains. To deal with …

While huge volumes of unlabeled data are generated and made available in many domains,
the demand for automated understanding of visual data is higher than ever before. Most …

Unsupervised domain adaption (UDA) aims to reduce the domain gap between labeled
source and unlabeled target domains. Many prior works exploit adversarial learning that …

The research of semantic segmentation based on unsupervised domain adaptation greatly
alleviates the high-cost bottleneck of manual annotation in deep learning. Inevitably domain …

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 …

Generalizing knowledge to unseen domains, where data and labels are unavailable, is
crucial for machine learning models. We tackle the domain generalization problem to learn …

Self-training approach recently secures its position in domain adaptive semantic
segmentation, where a model is trained with target domain pseudo-labels. Current …