Hybrid Spectral Denoising Transformer with Guided Attention
Zeqiang Lai, Chenggang Yan, Ying Fu

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRemote-Sensing Image Classification · Advanced Image Fusion Techniques · Image and Signal Denoising Methods
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Position-Wise Feed-Forward Layer · Dense Connections · Adam · Softmax · Residual Connection · Byte Pair Encoding · Label Smoothing
