Logarithm-transform aided Gaussian Sampling for Few-Shot Learning
This work addresses the challenge of adapting models to new classes with limited data in image classification, representing an incremental improvement over existing Gaussian-based methods.
The paper tackles the problem of few-shot image classification by proposing a novel Gaussian transform that better approximates Gaussian distributions from experimental data, resulting in significant performance gains with reduced data sampling.
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.