CGCNN:基于内容引导卷积神经网络的高光谱图像分类 | TGRS 2020
Posted 科研之高光谱
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了CGCNN:基于内容引导卷积神经网络的高光谱图像分类 | TGRS 2020相关的知识,希望对你有一定的参考价值。
△ 点 上方蓝字 关注科研之高光谱
分享前沿论文 享受科研之美
你好,今天介绍的论文来自南京理工大学肖亮老师团队,提出了基于内容引导卷积神经网络的高光谱图像分类。
这篇论文投稿于2019年10月22日,修改于2020年1月30日,收录于2020年2月7日。
卷积神经网络(CNNs)在高光谱图像(HSIs)分类中表现出了显著的性能。然而,由于目前的卷积核是固定形状,CNN对不同地物结构建模时存在固有的局限性,特别是在不同类边缘区域,不规则的类边界会导致分类误差较大。
Convolutional neural networks (CNNs) are of great interest and have demonstrated remarkable performance in hyperspectral images (HSIs) classification. However, due to the current configuration of the convolution layers with a fixed kernel shape, regular CNNs are inherently limited inmodeling the diverse land-cover structures, particularly in the cross-classes edge regions, where irregular class boundaries would lead to high classification errors.
To address this issue, we propose a content-guided CNN (CGCNN) for HSI classification. Compared with the shape-fixed kernel in the traditional CNN, the proposed content-guided convolution adaptively adjusts its kernel shape according to the spatial distribution of land covers.
The content pattern is reflected by a latent guide map automatically learned from HSI. Such content-adaptive kernel with CGCNN could suppress their regularity and unexpected features in class boundaries and, thus, improve the feature learning in cross-classes regions.
基于内容引导卷积,构建了一个新的引导特征提取单元(GFEU)来进行光谱-空间特征学习。最后,通过对多个紧密连接的GFEUs进行叠加,建立了CGCNN分类框架,有助于减少梯度消失,提高对过拟合的鲁棒性。
Based on the content-guided convolution, a novel guided feature extractionunit (GFEU) is constructed for spectral–spatial feature learning of HSI.Finally, the CGCNN classification framework is established by stacking multiple GFEUs with dense connection, which is helpful for mitigating the gradient vanishing and increasing the robustness to overfitting.
Extensive experiments on several HSIs demonstrate that the proposedapproach possesses great details’ preserving ability and its performance outperforms other state-of-the-art methods.
这篇论文从卷积神经网络中卷积核出发,基于高光谱图像的地物分布特性,自适应地调整卷积核形状,构建分类网络,我的思考如下:
第一,在改进卷积神经网络时,除了考虑地物分布不均匀外,还可以利用高光谱图像的其他特性,比如波段强相关性、空间高分辨率等。
第二,本文设计的自适应形状卷积核,除了改进常规的CNN外,还可以对其他的神经网络进行改进。
第三,这篇论文解决的问题是高光谱图像分类,还可以将其用于目标检测和语义分割等任务中。
祝身体健康,工作顺利!
往 期 解 读
1.
2.
以上是关于CGCNN:基于内容引导卷积神经网络的高光谱图像分类 | TGRS 2020的主要内容,如果未能解决你的问题,请参考以下文章