Cloudformer: Supplementary Aggregation Feature and Mask-Classification Network for Cloud Detection
Round 1
Reviewer 1 Report
This paper is well structured and contains relevant information in the field of remote sensing and geoinformatics.
It should interest experts in this field as well as many other readers.
Before publishing, I suggest that the article be checked
by an English language expert.
Author Response
Please see the attachment
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The authors have presented a well-balanced and detailed article about improving cloud segmentation. The article shows an extensive evaluation of the proposed approach. I have only two concerns - the related work doesn't cover some other relevant works in cloud/snow segmentation and deep learning in remote sensing:
- https://www.mdpi.com/2220-9964/10/7/462
- https://www.mdpi.com/2072-4292/10/11/1782
- https://www.mdpi.com/1424-8220/20/14/3906
- https://ieeexplore.ieee.org/abstract/document/1245253?casa_token=58n1q3pnV0oAAAAA:9_vs8XD7dBOLped2wsnZ3P9quXWNQ1WfPVsnxsVWTY1zCgMhF19sBmJDZmygBjayjj1H0rBOuGY
Another concern is the language. There are places where the text is formulated awkwardly. E.g., the first paragraph in the Experiments section reads "This section may be divided by subheadings. It should provide a concise and precise description of the experimental results, their interpretation, as well as the experimental conclusions that can be drawn". The text should be more formal and more confident. The section was already divided in subheadings so a better formulation can be:
"This section provides a concise and precise description of the experimental results..."
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 3 Report
Interesting paper for all who applied AI and those who investigate Clouds. However, the presented study is not adapted to the readers of the journal as the Applied sciences.
Not all readers are educated in AI methods and various modeling and simulation procedures. It is necessary to clarify what is FMask, CNN, short State of the Art and so on.
L156 - reference 25 is not Kirillov
Eq.1. All used variables must be explained after the eq., If some letters are used for constants - it needs to be stated (adding their values as well).
Same comment for equations that follow.
Table 1 - in needs to be indicated that for the mIou, mAcc and pACC are bolded the highest values while for the time is targeted the lowest value
Author Response
Please see the attachment
Author Response File: Author Response.pdf
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
