.png){kind=icon}
Return
Visual transductive learning via iterative label correction
.png){kind=icon}
OA
AI
DOI：10.1007/s00530-024-01339-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Unsupervised domain adaptation (UDA) aims to transfer knowledge across domains when there is no labeled data available in the target domain. In this way, UDA methods attempt to utilize pseudo-labeled target samples to align distribution across the source and target domains. To mitigate the negative impact of inaccurate pseudo-labeling on knowledge transfer, we propose a novel UDA method known as visual transductive learning via iterative label correction (VTL) that benefits from a novel label correction paradigm. Specifically, we learn a domain invariant and class discriminative latent feature representation for samples of both source and target domains. Simultaneously, VTL attempts to locally align the information of samples by learning the geometric structure of samples. Therefore, the novel label correction paradigm is utilized on embedded shared feature space to effectively maximize the reliability of pseudo labels by correcting inaccurate pseudo-labeled target samples, which significantly improves VTL classification performance. The experimental results on several object recognition tasks verified our proposed VTL superiority in comparison with other state-of-the-arts.
Keywords:
Unsupervised domain adaptation
Label correction
Progressive learning
Subspace learning
Journal
IF:
3.1
Papers:
2.8K
Citations:
2.7K
Organization
View more organizations
Cited Papers
Decoding the Structural Bases of D76N ß2-Microglobulin High Amyloidogenicity through Crystallography and Asn-Scan Mutagenesis.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveShareSave View more