Explore the Power of Dropout on Few-shot Learning
Computer Vision and Pattern Recognition
2023-01-27 v1
Abstract
The generalization power of the pre-trained model is the key for few-shot deep learning. Dropout is a regularization technique used in traditional deep learning methods. In this paper, we explore the power of dropout on few-shot learning and provide some insights about how to use it. Extensive experiments on the few-shot object detection and few-shot image classification datasets, i.e., Pascal VOC, MS COCO, CUB, and mini-ImageNet, validate the effectiveness of our method.
Keywords
Cite
@article{arxiv.2301.11015,
title = {Explore the Power of Dropout on Few-shot Learning},
author = {Shaobo Lin and Xingyu Zeng and Rui Zhao},
journal= {arXiv preprint arXiv:2301.11015},
year = {2023}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2210.06409