ML Anthology

Variational Few-Shot Learning

Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang
ICCV 2019
doi:10.1109/ICCV.2019.00177 /iccv/2019/zhang2019iccv-variational/

Abstract

We propose a variational Bayesian framework for enhancing few-shot learning performance. This idea is motivated by the fact that single point based metric learning approaches are inherently noise-vulnerable and easy-to-be-biased. In a nutshell, stochastic variational inference is invoked to approximate bias-eliminated class specific sample distributions. In the meantime, a classifier-free prediction is attained by leveraging the distribution statistics on novel samples. Extensive experimental results on several benchmarks well demonstrate the effectiveness of our distribution-driven few-shot learning framework over previous point estimates based methods, in terms of superior classification accuracy and robustness.

PDF ICCV Semantic Scholar

Cite

Text

Zhang et al. "Variational Few-Shot Learning." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00177

Markdown

[Zhang et al. "Variational Few-Shot Learning." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/zhang2019iccv-variational/) doi:10.1109/ICCV.2019.00177

BibTeX

@inproceedings{zhang2019iccv-variational,
  title     = {{Variational Few-Shot Learning}},
  author    = {Zhang, Jian and Zhao, Chenglong and Ni, Bingbing and Xu, Minghao and Yang, Xiaokang},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00177},
  url       = {https://mlanthology.org/iccv/2019/zhang2019iccv-variational/}
}