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, we are pleased to verify that you meet the reviewer's valuable feedback to improve your research.
Thank you for considering PeerJ Computer Science and submitting your work.
[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]
Abstract and Introduction: The abstract has been revised to include a comprehensive overview of the entire paper, detailing the background, problem statement, methodology, and key contributions. The introduction now explicitly states the research question and identifies the knowledge gap, linking it directly to the broader context and specific challenges addressed by the HSDNet model
.
Literature Review: The literature review section has been expanded to provide a more comprehensive overview of the state-of-the-art in few-shot semantic segmentation and its applications in agriculture. This includes discussions on recent advancements and their implications for the field, highlighting the practical implementations of few-shot semantic segmentation in agriculture
.
Visual Representations: Additional visual representations, such as diagrams and flowcharts, have been included to better illustrate the methodology and the HSDNet architecture. These visuals aid in understanding the technical aspects of the approach, making it more accessible and understandable to readers`
Detailed Methodology: The methods section has been enhanced to include detailed descriptions of the experimental setup, ensuring complete reproducibility. This includes a new table outlining the specific hardware configurations used for training and testing the models
.
Mathematical Formulations: The mathematical formulations and explanations are well-presented, providing a clear understanding of the underlying principles and methodologies employed. Additional context and justification for specific choices, such as the selection of the Sharpness-Aware Minimization (SAM) strategy and the rationale behind using Dice Loss, have been provided. This includes a detailed discussion on the theoretical foundation of SAM and the reasons for its selection, as well as an expanded discussion on Dice Loss
Robustness and Generalization: The revised manuscript includes a robust discussion on the generalization capabilities of the HSDNet model. This is supported by empirical evidence and theoretical justifications, demonstrating the model's effectiveness in new and unseen environments, which is critical for its application in poultry farming.
.
Statistical Analysis: The statistical rigor of the findings has been maintained, with clear, concise, and logical arguments supporting the results. The revisions have strengthened the validity of the findings, ensuring that the conclusions drawn are well-supported by the data.
Language Quality: Efforts have been made to improve the quality of English language usage throughout the manuscript. This includes thorough revisions to address language concerns, enhancing the clarity and readability of the text
.
Response to Reviewers: The responses to the reviewers' comments have been meticulously crafted, demonstrating a careful consideration of the feedback provided. Each point raised by the reviewers has been addressed in detail, showing a commitment to enhancing the quality of the manuscript based on constructive criticism
The authors have made changes according to the reviewers' suggestions.
The authors have made changes according to the reviewers' suggestions.
The authors have made changes according to the reviewers' suggestions.
The authors have made changes according to the reviewers' suggestions.
Dear authors,
You are advised to critically respond to all comments point by point when preparing a new version of the manuscript and while preparing for the rebuttal letter. Please address all the comments/suggestions provided by the reviewers.
Kind regards,
PCoelho
**PeerJ Staff Note:** Please ensure that all review and editorial comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff
The abstract should provide a concise overview of the entire paper, including the background, problem statement, methodology, and key contributions. However, the current abstract lacks information about the background and problem statement. It would be beneficial to include a brief introduction to the context of poultry farming and the challenges faced in this domain, which the proposed HSDNet model aims to address.
The literature review section could be expanded to provide a more comprehensive overview of the state-of-the-art in few-shot semantic segmentation and its applications in agriculture.
The paper could benefit from additional visual representations, such as diagrams or flowcharts, to better illustrate the methodology and the HSDNet architecture.
The research question and the identified knowledge gap could be stated more explicitly and concisely in the introduction section.
While the methods are described in detail, some aspects of the experimental setup, such as the specific hardware configurations used for training and testing the models, could be further elaborated upon to ensure complete reproducibility.
The mathematical formulations and explanations are well-presented, facilitating a clear understanding of the underlying principles and methodologies employed. However, it would be beneficial to provide more context and justification for the specific choices made, such as the selection of the Sharpness-Aware Minimization strategy and the rationale behind using Dice Loss.
While the authors have demonstrated the impact and novelty of their work, a more in-depth discussion of the limitations and potential future research directions could strengthen the paper.
The statistical analysis and significance testing of the results could be expanded upon, particularly in comparing the performance of HSDNet with other state-of-the-art methods.
The conclusions could be more explicitly linked to the original research question and hypotheses, ensuring that the findings directly address the stated objectives.
The authors could consider conducting additional experiments or analyses to further validate the robustness of their proposed model under different conditions or scenarios.
Novelty and Significance: The paper introduces a novel approach, HSDNet, which integrates few-shot learning into the poultry farming domain for semantic segmentation tasks. The authors highlight the challenges of applying traditional deep learning methods in this domain due to the need for extensive annotated data and the variability in breeding environments. The proposed method addresses these challenges by leveraging few-shot learning, enabling the model to adapt to new settings or species with a single input image while maintaining substantial accuracy.
The paper is based on the semantic segmentation of Smart Poultry farming. The authors have implemented HSDNet algorithm which is modified form of HDMNet. The performance of segmentation algorithm is validated by existing model.
In the dataset, it would be appreciable if only single animal is captured in one frame. However, novel algorithm implemented in existing dataset is also fine.
The algorithm is implemented, and the results are compared with the existing models. The author should include the already reported results of the existing models.
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.