论文标题
贝叶斯几次分类，一vs-eashpólya-gamma增强高斯流程
Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes
论文作者
论文摘要
几乎没有射击分类（FSC），即在标记为小的数据集的情况下，将分类器改编成看不见的类的任务是迈出类似人类的机器学习的道路的重要一步。贝叶斯的方法非常适合解决在几个场景中过度拟合的基本问题，因为它们允许从业者根据观察到的数据来指定先前的信念并更新这些信念。当代贝叶斯少量分类的方法在模型参数上保持后验分布，该分布速度很慢，需要缩放模型大小的存储。取而代之的是，我们提出了一个基于Pólya-Gamma增强和单VS-EAPH SOFTMAX近似的新组合的高斯过程分类器，该组合使我们能够在功能而不是模型参数上有效地边缘化。我们证明了标准的少数几个分类基准和少量射击域转移任务的精度和不确定性量化的提高。
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 Pólya-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.
