2023/09/28 by Vaibhav Ganatra, Ganatra, Vaibhav
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Gaussian #Gaussian process #Image (mathematics) #Image Processing Techniques and Applications #Logarithm #Machine learning #Mathematical analysis #Mathematics #Pattern recognition (psychology) #Probability distribution #Representation (politics) #Sampling (signal processing) #Shot (pellet) #Spectroscopy Techniques in Biomedical and Chemical Research #Statistics #Transformation (genetics)
paper · pdf · doi:10.48550/arxiv.2309.16337
openalex publication_date 2023/09/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.