A Hybrid Instance-based Transfer Learning Method

@article{Asgarian2018AHI,
  title={A Hybrid Instance-based Transfer Learning Method},
  author={Azin Asgarian and Parinaz Sobhani and Ji Chao Zhang and Madalin Mihailescu and Ariel Sibilia and Ahmed Bilal Ashraf and Babak Taati},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.01063}
}
In recent years, supervised machine learning models have demonstrated tremendous success in a variety of application domains. Despite the promising results, these successful models are data hungry and their performance relies heavily on the size of training data. However, in many healthcare applications it is difficult to collect sufficiently large training datasets. Transfer learning can help overcome this issue by transferring the knowledge from readily available datasets (source) to a new… CONTINUE READING
11
Twitter Mentions

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Instance-Weighted Transfer Learning of Active Appearance Models

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
  • 2010
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Effective injury prediction in professional soccer with gps data and machine learning

Alessio Rossi, Luca Pappalardo, +3 authors Daniel Medina
  • arXiv preprint arXiv:1705.08079,
  • 2017

Bayesian Active Appearance Models

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014

Face detection, pose estimation, and landmark localization in the wild

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 3 EXCERPTS