Robust Remote Sensing Image Cross-Scene Classification Under Noisy Environment

In recent years, great progress has been made in the field of cross-scene classification. However, most existing cross-scene methods assume that the source domain has massive and carefully annotated data, which is time-consuming and labor-intensive in practice. Datasets in real-life applications usually contain a large number of noisy labels, which will significantly affect cross-scene classification performance. How to perform more discriminative and generalized cross-scene classification in the presence of noisy samples needs to be urgently addressed. Apart from that, existing methods tend to implement global matching between domains, causing problems such as unbalanced adaptation and negative transfer, limiting the cross-scene performance of the model. For more effective and reliable cross-scene classification under noisy environment, robust adaptation with noise (RAN) is proposed in this article. RAN explores which samples are noiseless and transferable to enable positive and robust cross-scene transfer. The curriculum learning strategy is used to filter out noisy samples for better source supervised learning and cross-domain matching. To further improve the stability and effectiveness of cross-scene adaptation, the class weighting factor and the public weighting factor are introduced to consider the class information of the source and target domains. RAN is an efficient plug-and-play adaptation framework, which is easily implemented and can be embedded in existing methods. Experimental results demonstrate that the proposed RAN can achieve remarkable performance on cross-scene classification tasks in noisy environments.

I. Introduction

In recent years, scene classification has gained increasing attention in the field of remote sensing (RS). It attempts to build models that can discriminate the scene category of RS images. Not only does scene classification provide clues for other RS tasks, but also it is used in many real-world applications such as land use [1], urban planning [2], and environment and climate monitoring [3]. However, difficulty in acquiring high-quality labeled data and poor generalizability of models have seriously hampered the development and application of scene classification methods.