Optimizing distortion magnitude for data augmentation in few-shot remote sensing scene classification

Abstract

ABSTRACT In the domain of few-shot classification tasks for remote sensing images, the impact of data augmentation is often overlooked, and conventional methods offer only modest gains in classification performance. To better exploit the potential of data augmentation in few-shot learning, we propose an innovative data augmentation method tailored to optimize few-shot remote sensing scene classification. We begin by dissecting the relationship between various types of feature distortions and classification performance, introducing an optimal distortion magnitude estimation method for different feature types. Subsequently, we integrate multiple distortion magnitude optimization pathways into the model learning process, achieving a dual optimization of model parameters and distortion magnitudes. The extended data provide the model with distorted samples from multiple feature perspectives, and the dynamic optimization of distortion magnitudes enhances the effectiveness of the extended data for classification. Ultimately, we evaluate the performance of our method on general remote sensing datasets, demonstrating a significant advantage in classification accuracy over baseline methods. This approach offers a new perspective in robustness research for few-shot remote sensing scene classification models based on data augmentation.