Next Article in Journal
A Semi-Octagonal 40-Bit High Capacity Chipless RFID Tag for Future Product Identification
Previous Article in Journal
Warm Starting Variational Quantum Algorithms with Near Clifford Circuits
 
 
Article
Peer-Review Record

Semi-Supervised Remote Sensing Image Semantic Segmentation Method Based on Deep Learning

Electronics 2023, 12(2), 348; https://doi.org/10.3390/electronics12020348
by Linhui Li 1, Wenjun Zhang 1, Xiaoyan Zhang 1, Mahmoud Emam 2 and Weipeng Jing 1,*
Reviewer 2: Anonymous
Electronics 2023, 12(2), 348; https://doi.org/10.3390/electronics12020348
Submission received: 10 December 2022 / Revised: 31 December 2022 / Accepted: 4 January 2023 / Published: 9 January 2023

Round 1

Reviewer 1 Report

The manuscript entitled "Semantic Semi-supervised Remote Sensing Image Segmentation Method Based on Deep Learning" needs to be improved to be published in Electronics.

 

Abstract: The methodology is unclear.

Change "paper" to "study". And the same in the last paragraph of the introduction.

What does ISPRS mean? You should not use abbreviations in the abstract.

 

Related Word or Material and Methods?

 

Methods: Fig. 1 should appear after the callout in the text. The same is true for Figs 2, 3, 4, and 5.

Algorithm 1. It should be a Table with title and callout in the text.

 

Discussion: It should insert the name of the y-axis and the same scale. It shows who is a, b, and c in the chapter. Insert standard error or deviation of the mean.

 

Reference: All conference proceedings should be replaced by scientific articles.

Author Response

Dear reviewer 1: We would like to thank reviewers for their valuable feedback and constructive comments. We have carefully addressed all the raised concerns and problems. We have also improved the presentation and illustration. Below we present a detailed illustration of the changes that we have made in response to each raised comment. Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This study applies semi-supervised Deep Learning methods to remote sensing image semantic segmentation. The authors have done in good job in background reviews, methodology, experiment setup and result analysis. Before proceeding to publication, I just have one minor question regarding the implementation of experiments: Compared to the UNet and DeepLabV3 deep networks, what are the algorithm complexity and total training process efficiency in the authors' approach (total computational time and accumulated CPU/GRAPHIC usage)?

 

 

 

Author Response

Dear reviewer 2:We would like to thank you for their valuable feedback and constructive comments. We have carefully addressed all the raised concerns and problems. We have also improved the presentation and illustration. Below we present a detailed illustration of the changes that we have made in response to each raised comment. Please see the attachment.

Round 2

Reviewer 1 Report

The authors have corrected the manuscript as suggested.

Back to TopTop