Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples

TL;DR

This paper introduces a self-supervised learning approach for remote sensing image scene classification that outperforms traditional methods relying on ImageNet pre-training, especially when labeled data is scarce.

Contribution

The paper proposes a novel self-supervised learning mechanism tailored for remote sensing images, addressing the limitations of transfer learning from natural images.

Findings

SSL outperforms ImageNet pre-trained models on RSIs datasets.

Factors like self-supervised signals and domain differences significantly impact performance.

SSL effectively reduces dependence on labeled data for remote sensing tasks.

Abstract

With the development of deep learning, supervised learning methods perform well in remote sensing images (RSIs) scene classification. However, supervised learning requires a huge number of annotated data for training. When labeled samples are not sufficient, the most common solution is to fine-tune the pre-training models using a large natural image dataset (e.g. ImageNet). However, this learning paradigm is not a panacea, especially when the target remote sensing images (e.g. multispectral and hyperspectral data) have different imaging mechanisms from RGB natural images. To solve this problem, we introduce new self-supervised learning (SSL) mechanism to obtain the high-performance pre-training model for RSIs scene classification from large unlabeled data. Experiments on three commonly used RSIs scene classification datasets demonstrated that this new learning paradigm outperforms the traditional dominant ImageNet pre-trained model. Moreover, we analyze the impacts of several factors in SSL on RSIs scene classification tasks, including the choice of self-supervised signals, the domain difference between the source and target dataset, and the amount of pre-training data. The insights distilled from our studies can help to foster the development of SSL in the remote sensing community. Since SSL could learn from unlabeled massive RSIs which are extremely easy to obtain, it will be a potentially promising way to alleviate dependence on labeled samples and thus efficiently solve many problems, such as global mapping.