Variational Few-Shot Learning

By Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang. 2019

168 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging, Probabilistic & Bayesian Methods, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Min Xu
2. Lu Liu
3. Shuo Yang

In Radiology, Nuclear Medicine and Imaging

1. Min Xu
2. Lu Liu
3. Shuo Yang

Citations in the corpus

• Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness (2021, unknown): “Representative works include [56, 51, 19, 20, 22, 48, 7, 41, 6, 40, 36, 60, 45, 52, 64], etc.”
• Free Lunch for Few-shot Learning: Distribution Calibration (2021, background): “Zhang et al. (2019) tried to learn a variational autoencoder to approximate the distribution and predict labels based on the estimated statistics.”
• On Episodes, Prototypical Networks, and Few-shot Learning (2020, unknown): “5 Variatonal FSL (Zhang et al., 2019) 61.”