Explore the Power of Dropout on Few-shot Learning

TL;DR

This paper investigates how dropout, a regularization technique, can enhance the generalization ability of pre-trained models in few-shot learning tasks like object detection and image classification.

Contribution

It provides insights and empirical evidence on applying dropout to improve few-shot learning performance across multiple datasets.

Findings

Dropout improves generalization in few-shot tasks

Effective for object detection and image classification

Validated on Pascal VOC, MS COCO, CUB, and mini-ImageNet

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.