当前位置: X-MOL 学术Int. J. Comput. Vis. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DLRA-Net: Deep Local Residual Attention Network with Contextual Refinement for Spectral Super-Resolution
International Journal of Computer Vision ( IF 11.6 ) Pub Date : 2024-10-09 , DOI: 10.1007/s11263-024-02238-w
Ahmed R. El-gabri, Hussein A. Aly, Tarek S. Ghoniemy, Mohamed A. Elshafey

Hyperspectral Images (HSIs) provide detailed scene insights using extensive spectral bands, crucial for material discrimination and earth observation with substantial costs and low spatial resolution. Recently, Convolutional Neural Networks (CNNs) are common choice for Spectral Super-Resolution (SSR) from Multispectral Images (MSIs). However, they often fail to simultaneously exploit pixel-level noise degradation of MSIs and complex contextual spatial-spectral characteristics of HSIs. In this paper, a Deep Local Residual Attention Network with Contextual Refinement Network (DLRA-Net) is proposed to integrate local low-rank spectral and global contextual priors for improved SSR. Specifically, SSR is unfolded into Contextual-attention Refinement Module (CRM) and Dual Local Residual Attention Module (DLRAM). CRM is proposed to adaptively learn complex contextual priors to guide the convolution layer weights for improved spatial restorations. While DLRAM captures deep refined texture details to enhance contextual priors representations for recovering HSIs. Moreover, lateral fusion strategy is designed to integrate the obtained priors among DLRAMs for faster network convergence. Experimental results on natural-scene datasets with practical noise patterns confirm exceptional DLRA-Net performance with relatively small model size. DLRA-Net demonstrates Maximum Relative Improvements (MRI) between 9.71 and 58.58% in Mean Relative Absolute Error (MRAE) with reduced parameters between 52.18 and 85.85%. Besides, a practical RS-HSI dataset is generated for evaluations showing MRI between 8.64 and 50.56% in MRAE. Furthermore, experiments with HSI classifiers indicate improved performance of reconstructed RS-HSIs compared to RS-MSIs, with MRI in Overall Accuracy (OA) between 7.10 and 15.27%. Lastly, a detailed ablation study assesses model complexity and runtime.



中文翻译:


DLRA-Net:具有上下文优化功能的深度局部残差注意力网络,可实现频谱超分辨率



高光谱图像 (HSI) 使用广泛的光谱波段提供详细的场景洞察,这对于成本高昂且空间分辨率低的材料辨别和地球观测至关重要。最近,卷积神经网络 (CNN) 是多光谱图像 (MSI) 光谱超分辨率 (SSR) 的常见选择。然而,它们通常无法同时利用 MSI 的像素级噪声衰减和 HSI 的复杂上下文时空频谱特性。在本文中,提出了一种具有上下文优化网络的深度局部残余注意力网络 (DLRA-Net),以整合局部低秩谱和全局上下文先验,以改进 SSR。具体来说,SSR 被展开为情境注意力细化模块 (CRM) 和双局部残余注意力模块 (DLRAM)。CRM 被提出来自适应地学习复杂的上下文先验,以指导卷积层权重以改进空间恢复。而 DLRAM 捕获深度、精细的纹理细节,以增强恢复 HSI 的上下文先验表示。此外,横向融合策略旨在将获得的先验整合到 DLRAM 之间,以实现更快的网络收敛。在具有实际噪声模式的自然场景数据集上的实验结果证实了在相对较小的模型尺寸下具有卓越的 DLRA-Net 性能。DLRA-Net 显示平均相对绝对误差 (MRAE) 的最大相对改善 (MRI) 在 9.71% 和 58.58% 之间,参数降低在 52.18 到 85.85% 之间。此外,还生成了一个实用的 RS-HSI 数据集,用于评估显示 MRI 在 MRAE 中在 8.64% 到 50.56% 之间。此外,使用 HSI 分类器的实验表明,与 RS-MSI 相比,重建的 RS-HSI 的性能有所提高,MRI 的整体准确率 (OA) 在 7 之间。10% 和 15.27%。最后,详细的消融研究评估了模型的复杂性和运行时间。

更新日期:2024-10-10
down
wechat
bug