All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Dear authors,
Thank you for clearly addressing all of the reviewers' comments. Your article is accepted for publication now.
Best wishes,
[# PeerJ Staff Note - this decision was reviewed and approved by Rong Qu, a PeerJ Computer Science Section Editor covering this Section #]
Thank you to the researchers for making a nice revision.
.
.
.
Dear authors,
Your article has a few remaining issues. We encourage you to address the concerns and criticisms of the reviewer and resubmit your article once you have updated it accordingly.
Best wishes,
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
I reviewed the work "LOANet: a lightweight network using object attention for extracting buildings and roads from UAV aerial remote sensing images" in detail. I have stated the deficiencies of the study in the articles. Researchers have proposed a new model to extract buildings and roads with deep learning from unmanned aerial vehicle (UAV) remote-sensing images. The proposed network adopts an encoder-decoder architecture in which Light Dense Connected Network (LDCNet) is developed as the encoder. In the decoder part, dual multi-scale context modules consisting of the Atrous Spatial Pyramid Pooling module (ASPP) and Object Attention Module (OAM) are designed to capture more context information from feature maps of UAV remote sensing images.
The values given in the summary and the values given in the results section should be reviewed. There is an ambiguity here that is difficult to understand. A table related to the subject can be added in the literature review section. Thanks to the table to be added, it will be easier to follow the studies.
In the dataset section, the number of classes, the number of data in each class, etc. Presenting information is important. Information about the LoveDA and t CITY-OSM datasets should be given. Whether the results presented in Table 6 are classification results or segmentation results should be given in detail. Limitations of the study should be discussed in the Discussion section. Information about future work should be given. The conclusion section should be expanded by using the results obtained in the study. Finally, I would like to state that the study should be re-read by the researchers in order to correct the typos.
I want to point out that the paper is generally well-written. I think the paper will improve if the authors address the shortcomings noted in the revision.
The services of language experts are required.
What is the innovation of the Object attention module? Please explain the innovation carefully and explain its specific function in the network.
The authors mention LDCNet as a lightweight network in the main contribution, but the FPS metric is not mentioned in the quantitative results of the two datasets. Please explain the relationship between parameters, computation, and FPS metric.
Future directions should be based on the limitation of the current study and the expansion of the work.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.