ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising
This work addresses noise reduction in hyperspectral images, which is crucial for applications like classification and interpretation, but it appears incremental as it builds on existing deep learning and attention mechanisms.
The authors tackled hyperspectral image denoising by proposing an attention-based deep residual network that learns a mapping from noisy to clean images, achieving state-of-the-art performance in quantitative and visual evaluations.
Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation. In this paper, we propose an attention-based deep residual network to directly learn a mapping from noisy HSI to the clean one. To jointly utilize the spatial-spectral information, the current band and its $K$ adjacent bands are simultaneously exploited as the input. Then, we adopt convolution layer with different filter sizes to fuse the multi-scale feature, and use shortcut connection to incorporate the multi-level information for better noise removal. In addition, the channel attention mechanism is employed to make the network concentrate on the most relevant auxiliary information and features that are beneficial to the denoising process best. To ease the training procedure, we reconstruct the output through a residual mode rather than a straightforward prediction. Experimental results demonstrate that our proposed ADRN scheme outperforms the state-of-the-art methods both in quantitative and visual evaluations.