-
Examples include multi-channel singular spectrum analysis (MSSA) [37,38], damping order reduction method (DRR) [39,40]
→ \rightarrow →
method (DRR) [39,40]后缺句号 -
This makes it possible for CNN to denoise seismic data [56–59].
→ \rightarrow →
这个不确定,用It makes会不会好点 -
According to different network models, the existing denoising
algorithms can be roughly divided into three categories. The
first is
→ \rightarrow →
现有去噪算法分为三类,第二类三类分段,第一类不单独成段会不会不太对称 -
The decoding part converts the generated fixed vector into an output sequence. Autoencoder(AE) [60,61] is a typical encoding-decoding framework with numerous variations.
→ \rightarrow →
介绍编码解码框架的部分,解释完编码解码,直接就摆出几种具体框架,会不会不太友好。可不可以加一句,目前流行的这三种框架,然后再具体说明每种。 -
Becuase the only connection of the existing encoding-decoding framework is
→ \rightarrow →
Because 拼写错误 -
The third is a denoiser based on the Adversarial Generative Network (GAN).
→ \rightarrow →
Adversarial Generative Network 前两个写反了哦 -
A denoising device that uses the powerful learning ability of GAN to construct a denoising device [64–67].
→ \rightarrow →
此句表述有误 -
The other uses GAN to model the noise distribution and generate rich training data to generate rich training data to achieve blind denoising [68].
→ \rightarrow →
① The other特指两个或两部分中的另一个或另一部分,表示两个中“一个……另一个……”,常用结构式为:one…the other…
此处是说了两种,可否改成上述结构更好。
② generate rich training data to generate rich training data 写重复了 -
However, the only connection of the encoding-decoding framework is a fixed-length vector,
→ \rightarrow →
个人感觉,这个however有点突兀。前面只说提了一个新的网络,也没铺垫什么,然后就转折。 -
However, the only connection of the encoding-decoding framework is a fixed-length vector, making it difficult for the decoder to obtain sufficient information from the input data. ①
→ \rightarrow →
Becuase the only connection of the existing encoding-decoding framework is a fixed-length vector, making it difficult for the decoder to obtain sufficient information from the input data.②
这里的第①句与前文中介绍第二类编码解码框架部分的最后一句②几乎完全相同,没问题吗 -
patching, residual channel attention block and encoding-decoding sub-network, and supervised attention module.
→ \rightarrow →
这里的 residual channel attention block到底是blocks还是block,前面介绍的时候是blocks。(后面也有这个问题,请将所有确认一致)
闵老师说不滥用and,这里的多个and是否合适 -
The patch technology uses a H×W fixed window to slide 2-D
→ \rightarrow →
这里的符号系统是否要跟前面的(d=s+n) 保持一致 -
H and W denote the width and height of the patch, respectively
→ \rightarrow →
先说的H,应该先是height
but the only difference is that there is no overlap
→ \rightarrow →
这句怪怪的 -
The second part, the excitation operation includes two 1×1 convolution operations as follows:
o=δ(Conv(ReLU(Conv(z)))),(3)
→ \rightarrow →
ReLU也算是function,要不要和前面的函数的符号系统一致,δ在图中是sigmoid不一致 -
C. Encoder-Decoder Subnetwork
→ \rightarrow →
Subnetwork 中间有没有-,文中有些地方有,有些没有,请确认保持一致 -
The input patch is first compressed to extract hidden features, and
then expanded to reconstruct the input patch.
→ \rightarrow →
and可否去掉 -
式(5)的符号系统与前面一致否
-
The RCAB module weights the input X∈RC×H×W to obtain the weighted feature map Xfeat∈RC×H×W, (此句附近的X都有下面类似问题)
→ \rightarrow →
这里的X与前面的符号系统不一致 -
H and W denotes height and weight,
→ \rightarrow →
denotes ->denote -
式子(6)UpSampling应该是down吧,前面说的Xfeat作为down-sampling的输入。
where bilinear up-sampling with a scaling factor of 0.5 is
used instead of max-pooling,
→ \rightarrow →
这句中是up也应是down
scaling factor 还是 scale factor
此部分叙述中的up-sampling是否应改成式子中一样的形式 -
Among them, the input of the last two RCAB modules is composed of the output of the convolutional layer and the output of the corresponding RCAB module in the encoder.
→ \rightarrow →
two RCAB modules is composed of中的 is->are -
式子(8)中的符号系统与前文一致否
-
The module provides useful ground truth, and the generated attention maps further suppresses useless information.
→ \rightarrow →
suppresses->suppress -
The input of SAM is the output of the decoder Fin∈RC×H×W, the output includes denoised data and attention enhancement featuresFout∈RC×H×W, whereC is the number of channels,HandWare height and width respectively.
→ \rightarrow →
the output includes -> include -
First, Fin generates residualRS∈R1×H×Wthrough 1×1 convolution… attention enhancement feature Fout.
→ \rightarrow →
此部分的符号系统,跟图2不太匹配,还有些正体斜体,是否粗体,请自己核对一下。
Fin generates 单数还是复数 -
Before the algorithm starts, the input of the two stages is preprocessed.
→ \rightarrow →
two stages is ->are -
式子(9)第一个和最后一个符号错了, l对应l, r 对应 r
且请确保此处的符号系统与前文一致 -
The spliced data is decoded to get the output
→ \rightarrow →
这里的data是单数还是复数 -
式(16)与前面符号系统一致吗
Con正体,前面是斜体,concat与前面的Cat属同一类吗,为什么这里首字母不大写 -
式(20)和(21)中的(ˆIi,j,k−Ii,j,k)中是否都该有平方,是对(20)中的进行了更改,还是(20)写漏了。且式(21)中增加的那部分中的 SNR(ˆI−I) 中的I是符号使用是否有误
-
In this section, We conduct three experiments:
→ \rightarrow →
We -> we -
The experimental test data does not include training data, it includes four synthetic data and two field data.
→ \rightarrow →
does
it includes four
复数还是单数 -
One field data (field-data-1) is selected from Stratton survey
The other field data (field-data-2) uses the seismic data we collected, which contains 350 traces and 5,400 time samples (Figs.5(j)).
→ \rightarrow →
is
uses
contains
这两处单数还是复数 -
One group (without RCAB) removes RCAB and penalty item, and the other (with RCAB) only removes penalty item.
→ \rightarrow →
前边用的term,是否要一致(后文也有此情况) -
We observe that in two datasets, the algorithm with RCAB suppresses noise while protecting the effective signal well. ①
The results show that our method can reduce the loss of effective signal while suppressing noise.②
→ \rightarrow →
感觉while前后动词应形式一致 -
Results show that the RCAB module is very effective in protecting effective signals.
→ \rightarrow →
一个句子出现两个effective,可否换个词 -
The test data are selected from the additional three synthetic data.
→ \rightarrow →
前文中的data后一般用的单数形式,请确认其后一般用单数还是复数。确定后,所有的地方应一致。 -
Hence we will setα= 0.6 in the following experiments.
→ \rightarrow →
Hence后是否缺少逗号 -
The wavelet transform has the worst denoising effect, and there is a large amount of noise leakage in the removed noise.
→ \rightarrow →
此处表述是否有误,去除的噪声中有效信号泄漏。 -
The denoising data obtained by DnCNN and the proposed method removes most of the noise, and the signal becomes clearly visible.
→ \rightarrow →
removes->remove -
The RCAB module can protect the loss of effective signals
through feature weighting.
→ \rightarrow →
signals到底应该是复数还是单数,整篇文章都有此问题,有时候单数,有时候复数。请将所有用到的地方保持一致。
且前文使用的是 feature weighted。 -
In addition, in complex field data, DDAE-GAN is significantly better than the denoising effect of the three.
→ \rightarrow →
DDAE-GAN->DDAE-RCAB -
It suppressed irrelevant information and protected valid signals through feature weighting.
→ \rightarrow →
前文使用的是 feature weighted -
This paper took advantages of two technologies…One was to …The second is to …The third was to avoid excessive denoising by adding penalty items after the loss function.
→ \rightarrow →
含义不明,先说了本文利用两种技术的优点。后面有1 2 3,前2个是针对技术,应该与第3有区别。
且此处,3个地方的时态不一致(请确认要使用何种时态):
One was
The second is
The third was -
Experiments showed that the penalty
→ \rightarrow →
实验结果如果是客观存在的结果,是否用一般现在时 -
The proposed method had better denoising performance than the three four benchmark algorithms in both synthetic and field data.
→ \rightarrow →
the three four benchmark 写错了
另外,请确保时态正确 -
Fig. 2. Residual channel attention block (RCAB).
→ \rightarrow →
图3中的Residual channel attention block(RCAB)也是,确认每个单词首字母大写吗,全文保持一致 -
Fig. 3. Encoder-decoder subnetwork.
→ \rightarrow →
subnetwork中请确认是否使用-,全文保持一致
图3中的符号正斜体和文中有些不一致
文中使用的是UpSampling和DownSampling,与图中的不一致
请确认此图中的符号系统和文中解释的一致 -
所有图中使用到C×H×W的地方,确认是否加粗,与文中一致
-
Fig. 4. Supervised attention module (SAM).
→ \rightarrow →
确认此处每个单词首字母大写吗
图4中的符号系统与文中不一致,是否加粗,是否斜体。(几乎每个符号),请自己确认一下。 -
Fig. 11. 图注中,(e) wavelet transform ,多了空格
PS:
由于是先写在记事本的,粘贴过来公式没有改,但不影响修改哈。
参考文献未检查,太多了,请自己看看哇。