Nonlinear Activation-Free Contextual Attention Network for Polyp Segmentation
Round 1
Reviewer 1 Report
The paper introduces an innovative methodology for polyp segmentation using the Nonlinear Activation-Free and Uncertainty Context Attention Network (NAF_UCANet). The author effectively explains the proposed method, performs an ablation study, and conducts a thorough comparison with various state-of-the-art (SOTA) methods to demonstrate its effectiveness. However, some points in the paper require explanation to enhance the reader's understanding.
· The authors are requested to add a comparison table in the related work which shows the strengths and weaknesses of previous models.
· There is a lack of explanation regarding the selection of Res2Net over other baseline models.
· The authors are requested to add a comparison of other baseline networks in the ablation study.
· The authors should mention and display images of such cases, in which the model gives bad predictions.
· The authors should clearly mention if the whole dataset was augmented or only the training set.
Author Response
Dear Reviewer，
Thank you very much for your valuable comments and suggestions. We value your feedback on our research efforts and sincerely appreciate the time you take to carefully review our manuscripts. We have carefully considered your comments and have improved them accordingly in the revised version.
And we send our answers to your comments in the form of "Word". In the paper we have used the function of “Track Changes” in “Word” to facilitate you to see clearly the corresponding modified parts.
Please see the attachment.
Thank you again for your interest in and support of our research. We are very grateful for your comments, which have played an important role in improving and refining our paper.
Finally, please accept our most sincere thanks again.
Yours sincerely,
Weidong Wu
Author Response File: 
Author Response.docx
Reviewer 2 Report
The manuscript proposes a Nonlinear Activation-Free and Uncertainty Context Attention Network (NAF_UCANet) for accurate segmentation of colorectal polyps.
Results demonstrated good performance of the method.
I find the topic interesting and being worth of investigation and the document is well structured.
Although I propose the following comments/suggestions:
- Abstract should be better organized: problem, motivation, aim, methodology, main results, further impact of those results.
- Keywords should be in alphabetical order
- I strongly suggest authors from refraining using personal pronouns such as "we" and "our" throughout the text and I encourage them to write it in an impersonal form of writing.
- Fig. 1 is very small, it is barely readable
- Discussion should discuss the impact of the dynamic parameters of the proposed approach has on the obtained results and should provide the limitations of the proposed method.
Minor corrections are advised.
Author Response
Dear Reviewer，
Thank you very much for your valuable comments and suggestions. We value your feedback on our research efforts and sincerely appreciate the time you take to carefully review our manuscripts. We have carefully considered your comments and have improved them accordingly in the revised version.
And we send our answers to your comments in the form of "Word". In the paper we have used the function of “Track Changes” in “Word” to facilitate you to see clearly the corresponding modified parts.
Please see the attachment.
Thank you again for your interest in and support of our research. We are very grateful for your comments, which have played an important role in improving and refining our paper.
Finally, please accept our most sincere thanks again.
Yours sincerely,
Weidong Wu
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Most of my comments are addressed, and I recommend acceptance of this manuscript.
