Hybrid Spectral Denoising Transformer with Guided Attention

TL;DR

This paper introduces a Hybrid Spectral Denoising Transformer (HSDT) that effectively captures spatial-spectral correlations in hyperspectral images using a novel combination of spectral self-attention, separable convolution, and self-modulated feed-forward networks, achieving superior denoising performance.

Contribution

The paper proposes a hybrid transformer model with spectral-guided attention and separable convolution for hyperspectral image denoising, addressing limitations of CNNs in capturing global correlations.

Findings

HSDT outperforms state-of-the-art methods on multiple datasets.

The model maintains low computational complexity.

Effective in both simulated and real-world noise scenarios.

Abstract

In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral image denoising. Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility. To address these issues, we introduce a hybrid approach that combines the advantages of both models with a Spatial-Spectral Separable Convolution (S3Conv), Guided Spectral Self-Attention (GSSA), and Self-Modulated Feed-Forward Network (SM-FFN). Our S3Conv works as a lightweight alternative to 3D convolution, which extracts more spatial-spectral correlated features while keeping the flexibility to tackle HSIs with an arbitrary number of bands. These features are then adaptively processed by GSSA which per-forms 3D self-attention across the spectral bands, guided by a set of learnable queries that encode the spectral signatures. This not only enriches our model with powerful capabilities for identifying global spectral correlations but also maintains linear complexity. Moreover, our SM-FFN proposes the self-modulation that intensifies the activations of more informative regions, which further strengthens the aggregated features. Extensive experiments are conducted on various datasets under both simulated and real-world noise, and it shows that our HSDT significantly outperforms the existing state-of-the-art methods while maintaining low computational overhead. Code is at https: //github.com/Zeqiang-Lai/HSDT.