Comparative study of deep learning methods for one-shot image classification

Training deep learning models for images classification requires large amount of labeled data to overcome the challenges of overfitting and underfitting. Usually, in many practical applications, these labeled data are not available. In an attempt to solve this problem, the one-shot learning paradigm tries to create machine learning models capable to learn well from one or (maximum) few labeled examples per class. To understand better the behavior of various deep learning models and approaches for one-shot learning, in this abstract, we perform a comparative study of the most used ones, on a challenging real-world dataset, i.e Fashion-MNIST.