VIP内容

讲座A部分: https://atcold.github.io/pytorch-Deep-Learning/en/week13/13-1/

在本节中,我们将讨论传统卷积神经网络的结构和卷积。然后我们扩展到图域。我们理解了图的特征,并定义了图卷积。最后,我们介绍了频谱图卷积神经网络,并讨论了如何进行频谱卷积。

0:00:50 -传统ConvNets的架构 0:13:11 -传统ConvNets的卷积 0:25:29 -光谱卷积

讲座B部分: https://atcold.github.io/pytorch-Deep-Learning/en/week13/13-2/ 本节介绍了图卷积网络(GCNs)的完整谱,首先介绍了通过谱网络实现谱卷积。然后,它提供了关于模板匹配的其他卷积定义对图的适用性的见解,从而导致空间网络。详细介绍了采用这两种方法的各种体系结构及其优缺点、实验、基准和应用。

0:44:30 - GCNs谱 1:06:04 -模板匹配,各向同性GCNs和基准GNNs 1:33:06 -各向异性GCNs和结论

课程地址:https://atcold.github.io/pytorch-Deep-Learning/

成为VIP会员查看完整内容
1
27

最新论文

Hyperspectral pansharpening aims to synthesize a low-resolution hyperspectral image (LR-HSI) with a registered panchromatic image (PAN) to generate an enhanced HSI with high spectral and spatial resolution. Recently proposed HS pansharpening methods have obtained remarkable results using deep convolutional networks (ConvNets), which typically consist of three steps: (1) up-sampling the LR-HSI, (2) predicting the residual image via a ConvNet, and (3) obtaining the final fused HSI by adding the outputs from first and second steps. Recent methods have leveraged Deep Image Prior (DIP) to up-sample the LR-HSI due to its excellent ability to preserve both spatial and spectral information, without learning from large data sets. However, we observed that the quality of up-sampled HSIs can be further improved by introducing an additional spatial-domain constraint to the conventional spectral-domain energy function. We define our spatial-domain constraint as the $L_1$ distance between the predicted PAN image and the actual PAN image. To estimate the PAN image of the up-sampled HSI, we also propose a learnable spectral response function (SRF). Moreover, we noticed that the residual image between the up-sampled HSI and the reference HSI mainly consists of edge information and very fine structures. In order to accurately estimate fine information, we propose a novel over-complete network, called HyperKite, which focuses on learning high-level features by constraining the receptive from increasing in the deep layers. We perform experiments on three HSI datasets to demonstrate the superiority of our DIP-HyperKite over the state-of-the-art pansharpening methods. The deployment codes, pre-trained models, and final fusion outputs of our DIP-HyperKite and the methods used for the comparisons will be publicly made available at https://github.com/wgcban/DIP-HyperKite.git.

0
0
下载
预览
Top