Dual-Domain Masked Image Modeling: A Self-Supervised Pretraining Strategy Using Spatial and Frequency Domain Masking for Hyperspectral Data

TL;DR

This paper introduces a self-supervised pretraining method for hyperspectral images that employs dual-domain masking in spatial and frequency domains, significantly improving classification performance and training efficiency.

Contribution

The paper proposes a novel dual-domain masking strategy for hyperspectral data pretraining, enhancing spectral-spatial feature learning for transformer models.

Findings

Achieves state-of-the-art results on three hyperspectral classification benchmarks.

Demonstrates rapid convergence during fine-tuning.

Improves spectral-spatial feature extraction through dual-domain masking.

Abstract

Hyperspectral images (HSIs) capture rich spectral signatures that reveal vital material properties, offering broad applicability across various domains. However, the scarcity of labeled HSI data limits the full potential of deep learning, especially for transformer-based architectures that require large-scale training. To address this constraint, we propose Spatial-Frequency Masked Image Modeling (SFMIM), a self-supervised pretraining strategy for hyperspectral data that utilizes the large portion of unlabeled data. Our method introduces a novel dual-domain masking mechanism that operates in both spatial and frequency domains. The input HSI cube is initially divided into non-overlapping patches along the spatial dimension, with each patch comprising the entire spectrum of its corresponding spatial location. In spatial masking, we randomly mask selected patches and train the model to reconstruct the masked inputs using the visible patches. Concurrently, in frequency masking, we remove portions of the frequency components of the input spectra and predict the missing frequencies. By learning to reconstruct these masked components, the transformer-based encoder captures higher-order spectral-spatial correlations. We evaluate our approach on three publicly available HSI classification benchmarks and demonstrate that it achieves state-of-the-art performance. Notably, our model shows rapid convergence during fine-tuning, highlighting the efficiency of our pretraining strategy.