Meta Self-Supervised Learning for Distribution Shifted Few-Shot Scene Classification
Tengfei Gong, Xiangtao Zheng, Xiaoqiang Lu
Abstract
Few-shot classification tries to recognize novel remote sensing image categories with a few shot samples. However, current methods assume that the test dataset shares the same domain with the labeled training dataset where prior knowledge is learned. It is infeasible to collect a training dataset for each domain, since remote sensing images may come from various domains. Exploiting the existing labeled dataset from another domain (source domain) to help the target dataset (target domain) classification would be efficient. In this paper, both meta-learning and self-supervised learning are jointly conducted for few-shot classification. Specifically, meta-learning is executed over a pre-trained network for few-shot classification. Furthermore, self-supervised learning is exploited to fit the target domain distribution by training on unlabeled target domain images. Experiments are conducted on NWPU, EuroSAT and Merced datasets to validate the effectiveness.