Corpus ID: 186202575

Knowledge Transfer in Vision Recognition: A Survey

@inproceedings{Lu2019KnowledgeTI,
  title={Knowledge Transfer in Vision Recognition: A Survey},
  author={Ying Lu and Lingkun Luo and Di Huang and Yunhong Wang and Liming Chen},
  year={2019}
}
  • Ying Lu, Lingkun Luo, +2 authors Liming Chen
  • Published 2019
  • Computer Science
  • In this survey, we propose to explore and discuss the common rules behind knowledge transfer works for vision recognition tasks. To achieve this, we firstly discuss the different kinds of reusable knowledge existing in a vision recognition task, and then we categorize different knowledge transfer approaches depending on where the knowledge comes from and where the knowledge goes. Compared to previous surveys on knowledge transfer that are from the problem-oriented perspective or from the… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 148 REFERENCES

    Learning Transferable Features with Deep Adaptation Networks

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Transfer Learning for Visual Categorization: A Survey

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised Visual Domain Adaptation Using Subspace Alignment

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    A theory of learning from different domains

    VIEW 18 EXCERPTS
    HIGHLY INFLUENTIAL

    Discriminative and Geometry Aware Unsupervised Domain Adaptation

    VIEW 8 EXCERPTS

    Robust Transfer Metric Learning for Image Classification

    • Zhengming Ding, Yun Fu
    • Mathematics, Medicine, Computer Science
    • IEEE Transactions on Image Processing
    • 2017
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Distilling the Knowledge in a Neural Network

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    One-shot learning of object categories

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Is Learning The n-th Thing Any Easier Than Learning The First?

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL