Lightweight individual cow identification based on Ghost combined with attention mechanism

Lili Fu; Shijun Li; Shuolin Kong; Ruiwen Ni; Haohong Pang; Yu Sun; Tianli Hu; Ye Mu; Ying Guo; He Gong

doi:10.1371/journal.pone.0275435

Peer Review History

Original SubmissionMay 31, 2022
2 Aug 2022 Decision Letter - Tao Song, Editor PONE-D-22-15687Lightweight individual cow identification based on Ghost combined with attention mechanismPLOS ONE Dear Dr. Gong, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Sep 16 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Tao Song Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. We suggest you thoroughly copyedit your manuscript for language usage, spelling, and grammar. If you do not know anyone who can help you do this, you may wish to consider employing a professional scientific editing service. Whilst you may use any professional scientific editing service of your choice, PLOS has partnered with both American Journal Experts (AJE) and Editage to provide discounted services to PLOS authors. Both organizations have experience helping authors meet PLOS guidelines and can provide language editing, translation, manuscript formatting, and figure formatting to ensure your manuscript meets our submission guidelines. To take advantage of our partnership with AJE, visit the AJE website (http://learn.aje.com/plos/) for a 15% discount off AJE services. To take advantage of our partnership with Editage, visit the Editage website (www.editage.com) and enter referral code PLOSEDIT for a 15% discount off Editage services. If the PLOS editorial team finds any language issues in text that either AJE or Editage has edited, the service provider will re-edit the text for free. Upon resubmission, please provide the following: The name of the colleague or the details of the professional service that edited your manuscript A copy of your manuscript showing your changes by either highlighting them or using track changes (uploaded as a supporting information file) A clean copy of the edited manuscript (uploaded as the new manuscript file) 3. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: No ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: 1. The data set constructed by itself is not convincing, and the small number of pictures in the data set is even less convincing. The data set should include training data, validation data, and test data. To avoid overlap between training data and test data, training data and test data should come from different data sets. 2. There are many separate drawings and annotations in the paper, for example, Figure 2. Please check carefully and make modifications. 3. When using abbreviations, you should give the full name of the noun before using the abbreviation. 4. It is mentioned in the paper that empty convolution is used to replace ordinary convolution. Please explain the reason for doing so. 5. The ghost module and the convolutional blocking attention module are mentioned to improve ReNet50. Please explain why these two modules are used to improve ReNet50 instead of other modules. 6. The experimental results are not enough to prove that the improved model has a high recognition accuracy. It is hoped that the author can supplement the experiments to prove that the model is more competitive than other models. 7. In terms of identification of cows, heuristic algorithms (https://doi.org/10.1038/s41540-022-00233-w, DOI: 10.1109 / TCBB. 2021.3127271) and self-attention (DOI: 10.1186/ S12864-022-08687-2) and other deep learning models also have great application potential. I hope the author can make a reasonable introduction and analysis. Reviewer #2: Thanks for your contribution, your work is complete, but some experimental procedures need to be more clearly explained. 1. The explanation of CBAM in the “methodology theory” chapter is redundant with the content in “Convolutional block attention module” chapter. 2. Could you explain stage 1,2,3 in Figure 3, and if they are Ghost Modules, what's the difference between them? 3. Since it is a model built on the basis of ResNet50, why not compare it with ResNet50? 4. The models compared in this paper have been proposed for a long time. Has there been any research on the individual recognition models in recent years? ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0275435.r001
Revision 1
10 Aug 2022 Author Response Dear Editor and Reviewers， Thank you for your valuable comments on " Lightweight individual cow identification based on Ghost combined with attention mechanism "(ID: PONE-D-22-15687). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. The revised part has been used to track revisions and is named "revised manuscript with track changes" to be uploaded as a separate manuscript. The main corrections in the paper and the responds to the reviewer’s comments are as flowing: Reviewer #1: 1. Training data and test data overlap Answer: Thank you very much, I am Sorry for your misunderstanding due to my writing, we have enriched and refined the "data collection and processing" in the manuscript. Our data set is collected from the real farm, and all data has been uploaded to figshare. In this experiment, the data set is divided into 70% of the training set, 20% of the verification set and 10% of the test set. There is no overlapping image between the training data and the test data. 2. There are many separate drawings and annotations in the paper, for example, Figure 2. Please check carefully and make modifications. Answer: Thanks for the reminder, we have revised it. 3. When using abbreviations, you should give the full name of the noun before using the abbreviation. Answer: Thanks for the reminder, The full name of the noun has been given before using abbreviations. 4. It is mentioned in the paper that empty convolution is used to replace ordinary convolution. Please explain the reason for doing so. Answer: Thank you for your comments. In Section 3.1, we refine the reasons for using void convolution instead of ordinary convolution. Ordinary convolution cannot take into account both receptive field and parameter quantity. In order to lighten the model, we choose to use empty convolution that can satisfy large receptive field and less parameter quantity. 5. The ghost module and the convolutional blocking attention module are mentioned to improve ReNet50. Please explain why these two modules are used to improve ReNet50 instead of other modules. Answer: Thank you for your valuable opinions, firstly, resnet50 is a classical deep convolutional neural network and can be further lightweight. Secondly, as a deep convolution neural network, resnet50 will generate a large number of similar feature maps in the process of calculating features, and ghost module can efficiently generate these similar feature maps through simple linear operation. In addition, the structure of ghost module is very similar to that of resnetblock, so this study uses ghost module to improve resnet50. The addition of attention mechanism is only to further improve the accuracy of the model. 6. The experimental results are not enough to prove that the improved model has a high recognition accuracy. It is hoped that the author can supplement the experiments to prove that the model is more competitive than other models. Answer: Thank you for your comments, In the manuscript, we compared the model of this study with other classical convolutional neural network models, in which we supplemented the performance comparison of the new model just proposed in the last two years. In addition, we compared the model with the model proposed by other researchers in recent years for individual identification of cows, and compared it with our previous studies. The results showed that our model was improved compared with previous studies, and its performance was better than that of other researchers. 7. In terms of identification of cows, heuristic algorithms (https://doi.org/10.1038/s41540-022-00233-w, DOI: 10.1109 / TCBB. 2021.3127271) and self-attention (DOI: 10.1186/ S12864-022-08687-2) and other deep learning models also have great application potential. I hope the author can make a reasonable introduction and analysis. Answer: Thank you very much for your comments. We carefully read the two articles recommended by you and cited self-attention (DOI: 10.1186/s12864-022-08687-2), which enriched our manuscript. Special thanks to you for your good comments. Reviewer #2: 1. The explanation of CBAM in the “methodology theory” chapter is redundant with the content in “Convolutional block attention module” chapter. Answer: Thanks to your valuable comments, we found that it is indeed a duplicate, so we have deleted it, enriched and refined the " Convolutional block attention module" 2. Could you explain stage 1,2,3 in Figure 3, and if they are Ghost Modules, what's the difference between them? Answer: Thank you for your suggestion, fig. 3 is the model we built, in which stage1, stage2 and stage3 are added with different numbers of ghost in a progressive manner to ensure the depth of the model. At the same time, it follows the rule that the more the feature maps in the forward propagation process of the convolution neural network, the more convolution kernels are required. 3. Since it is a model built on the basis of ResNet50, why not compare it with ResNet50? Answer: Thank you for your comments, the comparison with resnet50 is not included in the " Model performance validation". In order to better show the effectiveness of the methods we used to improve, we put the comparison results between the model and the original model resnet50 in the " Ablation experiments". 4. The models compared in this paper have been proposed for a long time. Has there been any research on the individual recognition models in recent years? Answer: Thank you for your comments, in " Model performance validation ", the models we compare are all classical convolutional neural network models. According to your opinion, we have added two new models, EfficientNet v2 (2021) and PVT (2021). In addition, we compared with other methods of studying cows in recent years, and the results are shown in the manuscript. Special thanks to you for your good comments. We tried our best to improve the manuscript and made some changes in the manuscript. These changes will not influence the content and framework of the paper. We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval. Once again, thank you very much for your comments and suggestions. Attachments Attachment Submitted filename: Response to Reviewers .docx https://doi.org/10.1371/journal.pone.0275435.r002
19 Sep 2022 Decision Letter - Tao Song, Editor Lightweight individual cow identification based on Ghost combined with attention mechanism PONE-D-22-15687R1 Dear Dr. Gong, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Tao Song Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed Reviewer #2: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: The use of accurate and informative dairy farming is very interesting, and the authors have addressed all the comments in this revised version. Reviewer #2: (No Response) ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No ******** https://doi.org/10.1371/journal.pone.0275435.r003
Formally Accepted
20 Sep 2022 Acceptance Letter - Tao Song, Editor PONE-D-22-15687R1 Lightweight individual cow identification based on Ghost combined with attention mechanism Dear Dr. Gong: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Tao Song Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0275435.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .