Variational Few-Shot Learning
Lists
Only you see this
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.
BibTeX
@inproceedings{zhang2019variational,
author = {Jian Zhang and Chenglong Zhao and Bingbing Ni and Minghao Xu and Xiaokang Yang},
title = {{Variational Few-Shot Learning}},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/iccv.2019.00177},
}Loading related content...