Corpus ID: 220646921

Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation

@article{Peng2020Domain2VecDE,
  title={Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation},
  author={Xingchao Peng and Yichen Li and Kate Saenko},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.09257}
}
  • Xingchao Peng, Yichen Li, Kate Saenko
  • Published 2020
  • Computer Science
  • ArXiv
  • Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. A technique to measure domain similarity is critical for domain adaptation performance. To describe and learn relations between different domains, we propose a novel Domain2Vec model to provide vectorial representations of visual domains based on joint learning… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 117 REFERENCES
    Domain2Vec: Deep Domain Generalization
    • 2
    • PDF
    Moment Matching for Multi-Source Domain Adaptation
    • 104
    • Highly Influential
    • PDF
    VisDA: The Visual Domain Adaptation Challenge
    • 119
    • Highly Influential
    • PDF
    Unsupervised Domain Adaptation with Residual Transfer Networks
    • 591
    • PDF
    Open Set Domain Adaptation
    • 148
    • PDF
    Open Set Domain Adaptation for Image and Action Recognition
    • 14
    • PDF
    Partial Adversarial Domain Adaptation
    • 96
    • Highly Influential
    • PDF
    Deep Domain Confusion: Maximizing for Domain Invariance
    • 872
    • PDF