Variational Few-Shot Learning

Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 1685-1694

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhang_2019_ICCV,
author = {Zhang, Jian and Zhao, Chenglong and Ni, Bingbing and Xu, Minghao and Yang, Xiaokang},
title = {Variational Few-Shot Learning},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}