图3. GSA(Global Spectral self-Attention)模块前和后的特征图 GSA层获取了比NLSA层更有细节信息和结构纹理。由于波段之间存在密切关系,通过全局光谱自注意力,不同波段可以相互补充,从而产生更好的特征表达。 表3.模型复杂度比较 从上表可以看出,本文提出的SST方法能够在参数量较小运算量中等的情况下PSNR的值更高...
可以看出,方法的核心在于SSMA模块,即spatial-spectral multi-head self-attention,该模块结构如下图所示: 其实原理也非常简单,图中画的非常清楚了。需要注意的是,在 spatial attention 前有一个 shift operation,论文中说是在X,Y方向分别 shift 的尺寸为 M/2 个像素,代码为: shifted_x = torch.roll(x, shifts...
spatial-spectral self-attentionOmni-dimensional dynamic convolution can adjust spatial sizes, the amount of input/output channels, and kernel size based on the characteristics of the input, thus improving the capacity to extract characteristics through convolution, resulting in increased computation and ...
This study presents a spectral–spatial self-attention network (SSSAN) for classification of hyperspectral images (HSIs), which can adaptively integrate local features with long-range dependencies related to the pixel to be classified. Specifically, it has two subnetworks. The spatial subnetwork intro...
自注意力机制可以获得每两个波段的关系。例如,机载可见光/红外成像光谱仪(AVIRIS)包含224个波段。使用self-attention,通过学习过程可以得到一个形状为224×224的矩阵。矩阵中的每个元素代表两个波段之间的关系。如图1所示,上一部分CNN提取的特征然后被送Transformer学习长程依赖,主要包含三个元素。
Security Insights Additional navigation options master 1Branch0Tags Code This branch is up to date withxyvirtualgroup/TSA-Net:master. README TSA-Net for CASSI This repository contains the codes for paperEnd-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention(ECCV (2020...
Hyperspectral Image Classification Based on Two-Branch Multiscale Spatial Spectral Feature Fusion with Self-Attention Mechanisms In recent years, the use of deep neural network in effective network feature extraction ...
Spectral-Spatial Self-Attention Networks for Hyperspectral Image Classification 2022, IEEE Transactions on Geoscience and Remote Sensing Towards on-board hyperspectral satellite image segmentation: Understanding robustness of deep learning through simulating acquisition conditions 2021, Remote Sensing View all citi...
The CASSI system has a simple system structure and thus has received more attention in terms of reconfiguration algorithms. Proposed methods include end-to-end frameworks [130], deep unfolding frameworks [131], and others. The current state-of-the-art (SOTA) model, DAUHST [131], employs a ...
In this section, the spectral-spatial domain attention network (SSDA) architecture will be introduced in detail, which includes a spectral-spatial module, a domain attention module, and a multiple loss module. 3.1. SSDA Framework Figure 1 displays the training framework of the SSDA. In particular...