Bayesian Few-Shot Classification with One-vs-Each P\'olya-Gamma Augmented Gaussian Processes
ICLR(2020)
摘要
Few-shot classification (FSC), the task of adapting a classifier to unseen classes given a small labeled dataset, is an important step on the path toward human-like machine learning. Bayesian methods are well-suited to tackling the fundamental issue of overfitting in the few-shot scenario because they allow practitioners to specify prior beliefs and update those beliefs in light of observed data. Contemporary approaches to Bayesian few-shot classification maintain a posterior distribution over model parameters, which is slow and requires storage that scales with model size. Instead, we propose a Gaussian process classifier based on a novel combination of P\'olya-gamma augmentation and the one-vs-each softmax approximation that allows us to efficiently marginalize over functions rather than model parameters. We demonstrate improved accuracy and uncertainty quantification on both standard few-shot classification benchmarks and few-shot domain transfer tasks.
更多查看译文
关键词
classification,processes,few-shot,one-vs-each,olya-gamma
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络