Transferred Deep Learning-Based Change Detection in Remote Sensing Images

基于深度迁移学习的遥感图像变化检测(Transferred Deep Learning-Based Change Detection in Remote Sensing Images)论文详解

在解读该论文之前,先简单介绍两个简单的网络结构,第一个是2016年发表在ECCV的一篇文章《Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation》,该论文结构如下:
在这里插入图片描述
该网络结构主要是有三部分:
第一部分就是左边共有的部分:该部分提取特征。
第二部分是往右上走的分支:是对源域进行分类。
第三部分是往右下走的分支:该部分网络与第一部分正好相反,如果该部分最终的输出和原始第一部分的输入差距很小,我们就可以认为第一部分学习到的关于目标域的特征表达是有效的。当第三部分的loss趋于稳定时,则停止整个网络的训练。

第二个网络结构是U-net,该论文结构如下:
在这里插入图片描述
该模型由一条(contracting path)收缩路径(下采样,常规的卷积网络)和(expansive path)扩展路径(上采样,转置卷积网络)组成。共23个卷积层,模型的输入图像和输出图像的大小是不一样的,输出的图像比输入的要小。

1 基本介绍

1、这是2019发表在Geoscience and Remote Sensing的一篇文章。
2、首先在文章开始,作者阐述了motivation部分,第一个点是说监督的深度神经网络通常已经应用于很多不同的任务中,但是训练具有优越性能的这种深度神经网络需要大量标记数据。 然而,手动标记数据是耗时且昂贵的,尤其是对于遥感中的任务,例如变化检测。第二个点是作者又考虑到做迁移学习时源域与目标域的特征分布是不同的,这个缺点就会导致直接用源域训练的网络不能很好的适应到目标域中,因此作者引入了深度迁移学习的方法去解决这两个问题。
3、主要贡献
1)提出了一种转基于深度迁移学习的变化检测框架,其中未标记的图像从相关的标记图像中获得额外的知识。
2)在预训练阶段,提出重构检测网络(RDN)同时学习源域的变化检测任务和目标域(差分图像)的重建任务。 它可以从功能级别缓解源域和目标域之间的分布差异。该贡献的主要思想是来自2016年发表在ECCV的重构分类文章。
3)在fine-tune阶段,提出了基于区域和边界的策略来选择具有通过无监督方法正确分类的高可能性的像素。

2方法

在这里插入图片描述

2.1主要结构

这个网络也可以看作是两大部分:第一部分是预训练阶段,第二部分是fine-tune阶段。
预训练阶段,可以看作是三部分,分别是对源域的变化检测、对目标域差分图像的重构和前两小部分网络整体集成的网络(也就是作者说的重构检测网络RDN)。在整个RDN网络使用的是U-net网络结构,在这个过程中,作者提出了用合并一对patch去
评估U-net网络结构模式。
在预训练结束,对整个网络进行fine-tune。

2.2 具体训练过程

预训练阶段有三部分,首先用source data训练用于变化检测那部分的网络,其次是用目标域数据训练重构差分图像网络的部分,其中两个网络的低层部分是共享的,最后是训练整个RDN,损失函数定义如下:
1)变化检测网络的loss:
L s = − ∑ i = 1 N s ∑ i = 1 m ∑ j = 1 m l b c e ( y k s ( i , j ) , y ^ k s ( i , j ) ) L^{s}=-\sum_{i=1}^{N_{s}}\sum_{i=1}^{m}\sum_{j=1}^{m}l_{bce}(y_{k}^{s}(i,j),ŷ_k^s (i,j)) Ls=i=1Nsi=1m

Gas Metal Arc Welding (GMAW) is a widely used welding process in which a consumable metal wire electrode is fed into a weld pool to join two or more metal parts together. During the welding process, the electrode melts and forms a molten metal pool, which then cools and solidifies to form a welded joint. One way to analyze the GMAW process is to examine the metal-transfer images that are generated during welding. Metal-transfer images are high-speed photographs or videos of the GMAW process that capture the behavior of the molten metal as it is transferred from the electrode to the workpiece. Analyzing these images can provide insights into the physical processes that occur during welding, such as droplet detachment, droplet formation, and arc behavior. There have been several studies that have analyzed metal-transfer images in the GMAW process. One such study was conducted by Liu et al. (2017), who used high-speed photography to capture metal-transfer images during GMAW of aluminum alloys. They found that the droplet detachment frequency was influenced by the welding current, and that there was a critical current level above which the droplet detachment frequency increased dramatically. Another study by Liao et al. (2019) analyzed metal-transfer images during GMAW of high-strength steel. They found that the droplet transfer mode shifted from globular to spray transfer as the welding current increased, and that the formation of an unstable arc affected the droplet detachment process. Other researchers have used image processing techniques to analyze metal-transfer images. For example, Zhang et al. (2019) developed an algorithm to automatically detect and track the movement of droplets in metal-transfer images during GMAW. They found that the droplet size and transfer frequency were affected by the welding current and the wire feed speed. Overall, the analysis of metal-transfer images in the GMAW process is an active area of research that has the potential to improve our understanding of the physical processes that occur during welding. By studying metal-transfer images, researchers can gain insights into the factors that affect droplet detachment, droplet formation, and arc behavior, which can in turn help to optimize the welding process for different materials and applications.
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值