Masked Graph Convolutional Network for Small Sample Classification of Hyperspectral Images
Round 1
Reviewer 1 Report (Previous Reviewer 1)
The authors did the corrections.
Author Response
Thank you for what you have done.
Reviewer 2 Report (Previous Reviewer 2)
1. Do not use words such as we in the abstract, a more objective description is needed.
2.There are some enhancements compared to the previous article, and obvious errors have been fixed.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 3 Report (Previous Reviewer 4)
Please see the attached file.
Comments for author File: 
Comments.pdf
Author Response
Please see the attachments
Author Response File: Author Response.docx
Round 2
Reviewer 3 Report (Previous Reviewer 4)
See the attached file.
Comments for author File: Comments.docx
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.
Round 1
Reviewer 1 Report
Please check the numbers before the topic... introduction actually begins with 0.
Introduction: I liked how the authors linked the topics and brought me to the goal. However, it is a little longer in length than the normal introduction in the Remote sensing journal. In addition, figure 2, was not found any call for them.
How was the GSD affected in the classification method developed? This is important to point out once GSD in the IP site is bigger than others. I expect to read about it.
The authors conclude: "the proposed method can achieve better classification results than the existing advanced methods." How much better it was? I mean in number compared with the traditional methods tested.
"4. This paper shows great similarity with the following paper in the technical route and the selected data set. It is hoped that the author can further improve the content of the article and show innovation."
ZUO Xibing, LIU Bing, YU Xuchu, et al. Graph convolutional network method for small sample classification of hyperspectral images. Acta Geodaetica et Cartographica Sinica, 2021, 50(10): 1358-1369. DOI: 10.11947/j.AGCS.2021.20200155
Reviewer 2 Report
1.It should be meta-learning in line 72.
2.Full name of UP,IP,SA in Table1 should be introduced.
3.RULBP was introduced in this paper, but it was not used in the following result table, or is the LBP in the following text the above RULBP ? Need to confirm.
4.This paper shows great similarity with the following paper in the technical route and the selected data set. It is hoped that the author can further improve the content of the article and show innovation.
ZUO Xibing, LIU Bing, YU Xuchu, et al. Graph convolutional network method for small sample classification of hyperspectral images. Acta Geodaetica et Cartographica Sinica, 2021, 50(10): 1358-1369. DOI: 10.11947/j.AGCS.2021.20200155
Reviewer 3 Report
The paper deals with the identification by AI algorithms of hyperspectral images. The paper is quite complete, but it lacks of an introduction on the application of such type of images. Some typo should be addressed, such as line 109 "extracted", and many others...). Moreover, the paper reports about the hardware employed, but authors didn't reports about the computation time of their algorithm and didn't compare with the others used as benchmarking.
Reviewer 4 Report
Please see the attached file.
Comments for author File: Comments.pdf
