Capsule Broad Learning System Network for Robust Synthetic Aperture Radar Automatic Target Recognition with Small Samples
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsComments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe paper describe the Capsule Broad Learning System Network for Robust SAR ATR (CBLS-SARNET) and how it performs other deep learning methods in terms of recognition accuracy and training time. The apper seems to be well organized. The authors must improve their figure quality and graphics.
Author Response
Dear Reviewer,
Thank you for your constructive feedback and the positive remarks on the organization of our paper and the description of the Capsule Broad Learning System Network for Robust SAR ATR (CBLS-SARNET). We are pleased to hear that the structure and content of our manuscript meet your expectations.
Regarding your comment on enhancing the quality of figures and graphics, we acknowledge the importance of clear and high-quality visual representations to effectively communicate our findings. We are committed to addressing this feedback by undertaking the following steps:
Resolution Improvement: We will ensure that all figures are rendered in high resolution to improve clarity and visibility, especially when viewed in digital formats.
Consistency in Style: We will standardize the style, colors, and fonts across all figures and graphics to maintain consistency and professionalism throughout the document.
Enhanced Labeling and Annotations: We will review and revise the labeling and annotations in our figures to ensure they are clear, precise, and helpful for the reader.
These improvements will be implemented in the revised version of the manuscript to ensure that the visual elements effectively complement and elucidate the textual content.
Thank you once again for your valuable feedback, which helps us refine our presentation and improve the overall quality of our work.
Reviewer 3 Report
Comments and Suggestions for AuthorsThis paper puts forth a novel and distinctive network dubbed Capsule Broad Learning System Network for Robust SAR ATR (CBLS-SARNET), which is specifically tailored to cater to small-sample SAR ATR scenarios. But there are still several questions:
1. Table 3: “Learning Tate” ==> “Learning Rate”
2. Section 4.3: what are the conditions under which Figure 6 was obtained, and is the data in the figure the highest recognition accuracy that can be achieved for each activation function?
3. Section 4.4: why was Inceptionv3 used for the comparison test instead of Inceptionv4? Is Inceptionv4 not suitable for SAR image recognition in small sample conditions?
4. Section 4.5.2: the text mentions that “Analysis of recognition results demonstrates that despite a decrease in accuracy after introducing Gaussian noise, it remains within an acceptable range.” What are the criteria for this "acceptable range"?
Comments on the Quality of English LanguageMinor editing of English language required
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 4 Report
Comments and Suggestions for AuthorsPlease see the attached file.
Comments for author File: Comments.pdf
Comments on the Quality of English LanguageMinor editing of English language required.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf