Few-shot image classification has recently witnessed the rise of representation learning being utilised for models to adapt to new classes using only a few training examples. Therefore, the properties of the representations, such as their underlying probability distributions, assume vital importance. Representations sampled from Gaussian distributions have been used in recent works, [19] to train classifiers for few-shot classification. These methods rely on transforming the distributions of experimental data to approximate Gaussian distributions for their functioning. In this paper, I propose a novel Gaussian transform, that outperforms existing methods on transforming experimental data into Gaussian-like distributions. I then utilise this novel transformation for few-shot image classification and show significant gains in performance, while sampling lesser data.

翻译：少样本图像分类近年来见证了表示学习被用于模型仅通过少量训练样本适应新类别的兴起。因此，表示的特性（如其潜在概率分布）变得至关重要。近期工作中，[19]使用了从高斯分布采样的表示来训练少样本分类的分类器。这些方法依赖于将实验数据的分布变换为近似高斯分布以实现其功能。本文提出了一种新颖的高斯变换，在将实验数据转换为类高斯分布方面优于现有方法。随后我将这种新颖变换用于少样本图像分类，并在采样较少数据的情况下展示出显著的性能提升。