Dear Dr. Lei,

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 Jun 12 2025 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.

• 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,

Alessio Plebe

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. 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, we expect all author-generated code to 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.

3. Thank you for stating the following financial disclosure:

“This research was supported in part by the International Strategic Innovative Project of the National Key Research and Development Program of China under Grant(No. 2023YFE0112500)”

Please state what role the funders took in the study.  If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."

If this statement is not correct you must amend it as needed.

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

4. Thank you for stating the following in the Acknowledgments Section of your manuscript:

“This research was supported in part by the International Strategic Innovative Project of the National Key Research and Development Program of China under Grant(No. 2023YFE0112500)”

We note that you have provided funding information that is currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form.

Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows:

“This research was supported in part by the International Strategic Innovative Project of the National Key Research and Development Program of China under Grant(No. 2023YFE0112500)”

Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

5. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process.

Additional Editor Comments:

As you can discern from the reviews, significant improvements are needed for the manuscript to reach a publishable standard.

Additionally, it is worth noting that since the manuscript proposes a new software, it must be open source and stored in an appropriate archive, conform to the Open Source Definition, and complete with all necessary information for its installation and execution.

[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?

Reviewer #1: No

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

Reviewer #1: No

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: No

Reviewer #2: Yes

**********

Reviewer #1: While the manuscript proposes a promising object detection framework and presents encouraging experimental results, the theoretical foundation contains a critical misinterpretation.

1. Theoretical clarity on HGNetv2 vs RT-DETR. The manuscript incorrectly refers to HGNetv2 as the "RT-DETR backbone network" (e.g., Lines 50–51, 125–126). This is misleading—HGNetv2 is a CNN backbone that can be used within models like RT-DETR, but it is not part of RT-DETR’s transformer-based architecture. This conceptual confusion weakens the theoretical grounding and should be corrected throughout the manuscript to accurately reflect HGNetv2’s role as a standalone CNN backbone integrated with YOLOv8 in this work.

2. Figure 1 notation and clarification. The manuscript refers to “dot lines” in Figure 1, but the lines are red dashed lines. The terminology should be corrected for clarity. Additionally, multiple red dashed boxes are used—each box’s function should be clearly labeled or described in the caption.

3. Figure 2 – incomplete HG-block architecture. Figure 2, titled "The Network Architecture of HG-Block," fails to show the architecture in sufficient detail. Modules such as “CBA[4]”, “CBA[5]”, etc., appear without any explanation. Please define what ConvBAct (CBA) means and describe each block’s function. A clear legend and detailed block-level diagram are recommended.

4. Equation symbols. Several equations throughout the manuscript use variables (e.g., , , , , , etc.) without proper definitions or descriptions. All symbols should be explicitly defined when first introduced to ensure clarity and reproducibility.

5. Figure 4 – Visual overlap issue. In Figure 4, the overlay of text and image elements reduces legibility. Please adjust the layout to ensure all components (e.g., arrows, letters, and labels) are clearly visible and non-overlapping.

6. Check the usage of the language.

Reviewer #2: The manuscript "EdgeCaseDNet: An Enhanced Detection Architecture for Edge Case Perception in Autonomous Driving" addresses critical challenges in the field and proposes several meaningful enhancements to the YOLOv8 architecture. While the experimental results are convincing, showing substantial improvements over the YOLOv8 baseline and other comparison methods, there are several issues with the presentation that should be addressed before publication.

1. While there is an ablation study, it could benefit from a more detailed analysis of why each component contributes to the observed improvements.

2. The construction of the DEAP dataset would strengthen the paper, particularly regarding how edge cases were identified and selected.

3. While the authors mention reducing parameters and computational complexity throughout the paper, it lacks an in-depth computational analysis. A more comprehensive analysis of inference time and computational requirements would strengthen the practical applicability claims.

4. The manuscript contains numerous grammatical errors and awkward phrasings that impede comprehension. For example:

4.1 Line 74-75: "These methods are cumbersome, have poor generalization and robustness, and cannot meet practical road-scenario detection requirements." This is an overgeneralization without supporting evidence.

4.2 Line 149-151: "The Tiny model contains only three LDS Layers to maximize the GPU computation efficiency." The causal relationship is not clearly explained.

4.3 Line 238-239: " ∈[1, e) increases the focus on anchors of average quality." The meaning of "anchors of average quality" is not defined.

5. The term "edge case" is central to the paper, but it is never precisely defined. What constitutes an edge case versus a normal case should be clearly stated.

6. In Section 3.2, "Partial Convolution (PConv)" is introduced, but its mathematical formulation is missing, unlike that of other components.

7. The paper alternates between "HPDSCM" and "HPDSConv" when referring to the same module.

Minor changes:

1. The description of performance improvements appears in nearly identical form in the abstract, introduction, and conclusion.

2. The explanation of the CIoU loss function's limitations is repeated in similar terms in lines 229-232 and again when introducing the Wise-IoU loss.

3. The references to the figures are inconsistent in the manuscript. "Figure 1 shows the...." should be "Fig. 1. shows the...."

4. Figure 1 is cluttered, especially the HPDSCM, which is quite small and difficult to follow.

**********

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.

Dear Dr. Lei,

Please submit your revised manuscript by Oct 30 2025 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.

• 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,

Alessio Plebe

Academic Editor

PLOS ONE

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. 

Additional Editor Comments:

Reviewer #1:

Reviewer #3:

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #1: All comments have been addressed

Reviewer #3: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions??>

Reviewer #1: Yes

Reviewer #3: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: Yes

Reviewer #3: No

**********

4. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: Yes

Reviewer #3: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

Reviewer #3: Yes

**********

Reviewer #1: The revised copy has solved all my concerns in the first round of review process. So, I think the current copy is ready to be published.

Reviewer #3: This paper addresses edge-case perception in autonomous driving by introducing the DEAP dataset (13,030 images from SODA10M and CODA, augmented for adverse weather like fog, rain, snow, and night) and proposing EdgeCaseDNet, a YOLOv8-based model with enhancements including a Haar_HGNetv2 backbone for better feature extraction

1. The core contributions are primarily combinations of existing techniques rather than fundamental innovations. Haar wavelets have been used in computer vision for decades, AFPN and Wise-IoU are from prior work, and HPDSConv appears to be a straightforward combination of depthwise separable and partial convolutions. The authors are encouraged to clarify their contributions more clearly.

2. The DEAP dataset claims comprehensiveness with only 13,030 samples, which seems insufficient for robust edge case representation. The selection criteria from SODA10M and CODA are not clearly explained.

3. The 7:2:1 split is standard, but potential class imbalance (e.g., few tricycles) may bias results. Table 1 lists only a single “train/val number” per class (e.g., Car 49,771 vs Tricycle 346), which suggests severe imbalance yet no stratification strategy, per-condition counts (night/rain/fog/snow), or per-split class statistics are reported. Supply train/val/test counts per class and per condition, plus sampling policies to avoid leakage.

4. The evaluation is limited to the authors' own dataset. This needs more work, as well as clarification about the scope and limitation of the dataset.

5. The comparison primarily includes older YOLO versions and lacks comparison with recent state-of-the-art edge case detection methods.

6. The paper provides no statistical significance testing, limited computational analysis, and insufficient hardware specifications. The three test scenarios are too limited for comprehensive edge case evaluation.

7. While Equation (1) correctly presents the Haar transform, several equations (e.g., Equations 2, 3) unnecessarily complicate standard operations. The notation could be more concise and consistent.

8. The paper lacks analysis of failure cases.

9. Missing detailed computational cost analysis despite efficiency claims.

10. Multiple grammatical errors throughout, including inconsistent terminology ("DEAT dataset" vs "DEAP dataset"), awkward sentence constructions, and unclear technical explanations.

11. The paper provides insufficient justification for why Haar wavelets specifically benefit edge case detection.

12. It seems that the paper mixes mAP50-95 with “mAP50-90” and uses non-standard descriptions.

13. Claims of “real-time” are unsubstantiated: no latency/FPS/memory is reported. GFLOPs are listed in ablations, but input resolution is unspecified, making them uninterpretable. Add end-to-end latency (ms), FPS, peak memory, and evaluation thresholds on the same hardware.

**********

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 #3: 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.

EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving

PONE-D-25-09823R2

Dear Dr. Lei,

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 will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager®  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support .

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,

Alessio Plebe

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

This latest version of the manuscript has satisfactorily resolved the remaining

comments that emerged in the last round of review.

Therefore, the work can now be considered ready for publication.

Reviewers' comments: