Improved Quasi-Recurrent Neural Network for Hyperspectral Image Denoising

TL;DR

This paper enhances the QRNN3D model for hyperspectral image denoising by introducing an adaptive fusion module and other techniques, significantly improving its performance across various noise conditions.

Contribution

The paper proposes simple yet effective modifications to QRNN3D, including an adaptive fusion module and training strategies, to substantially boost hyperspectral image denoising performance.

Findings

Improved denoising accuracy on multiple noise levels

Superior performance compared to baseline models

Effective feature fusion and training techniques

Abstract

Hyperspectral image is unique and useful for its abundant spectral bands, but it subsequently requires extra elaborated treatments of the spatial-spectral correlation as well as the global correlation along the spectrum for building a robust and powerful HSI restoration algorithm. By considering such HSI characteristics, 3D Quasi-Recurrent Neural Network (QRNN3D) is one of the HSI denoising networks that has been shown to achieve excellent performance and flexibility. In this paper, we show that with a few simple modifications, the performance of QRNN3D could be substantially improved further. Our modifications are based on the finding that through QRNN3D is powerful for modeling spectral correlation, it neglects the proper treatment between features from different sources and its training strategy is suboptimal. We, therefore, introduce an adaptive fusion module to replace its vanilla additive skip connection to better fuse the features of the encoder and decoder. We additionally identify several important techniques to further enhance the performance, which includes removing batch normalization, use of extra frequency loss, and learning rate warm-up. Experimental results on various noise settings demonstrate the effectiveness and superior performance of our method.