One of important areas of machine learning research is zero-shot learning. It is applied when properly labeled training data set is not available. A number of zero-shot algorithms have been proposed and experimented with. However, none of them seems to be the "overall winner". In situations like this, it may be possible to develop a meta-classifier that would combine "best aspects" of individual classifiers and outperform all of them. In this context, the goal of this contribution is twofold. First, multiple state-of-the-art zero-shot learning methods are compared for standard benchmark datasets. Second, multiple meta-classifiers are suggested and experimentally compared (for the same datasets).
@article{arxiv.2203.15158,
title = {Practical Aspects of Zero-Shot Learning},
author = {Elie Saad and Marcin Paprzycki and Maria Ganzha},
journal= {arXiv preprint arXiv:2203.15158},
year = {2022}
}