On Parameter Tuning in Meta-learning for Computer Vision
Computer Vision and Pattern Recognition
2020-03-03 v1 Machine Learning
Abstract
Learning to learn plays a pivotal role in meta-learning (MTL) to obtain an optimal learning model. In this paper, we investigate mage recognition for unseen categories of a given dataset with limited training information. We deploy a zero-shot learning (ZSL) algorithm to achieve this goal. We also explore the effect of parameter tuning on performance of semantic auto-encoder (SAE). We further address the parameter tuning problem for meta-learning, especially focusing on zero-shot learning. By combining different embedded parameters, we improved the accuracy of tuned-SAE. Advantages and disadvantages of parameter tuning and its application in image classification are also explored.
Cite
@article{arxiv.2003.00837,
title = {On Parameter Tuning in Meta-learning for Computer Vision},
author = {Farid Ghareh Mohammadi and M. Hadi Amini and Hamid R. Arabnia},
journal= {arXiv preprint arXiv:2003.00837},
year = {2020}
}
Comments
6 pages, 2 algorithms, 3 figures