Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained base model to get better generalized novel model. Following theoretical analysis proves its rationality as well as indication of how to train a well-generalized base model. We then conduct experiments on four benchmarks and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75% on 5-shot miniImageNet which approximately outperforms existing methods by 10%.
@article{arxiv.1911.10807,
title = {Generalized Adaptation for Few-Shot Learning},
author = {Liang Song and Jinlu Liu and Yongqiang Qin},
journal= {arXiv preprint arXiv:1911.10807},
year = {2020}
}
Comments
We found a bug in the script in reexamining some of this work. We decide to withdraw for further modification