Gene

Detector

Algorithm

Bayesian probability

Metallurgy

Materials science

Robustness (evolution)

Shot noise

Telecommunications

Classifier (UML)

Economics

Biochemistry

Computer science

Pattern recognition (psychology)

Inference

Operations management

Artificial intelligence

Chemistry

Metric (unit)

Shot (pellet)

Machine learning

Bayesian inference

Computer vision

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.

Variational Few-Shot Learning