Road Anomaly Detection with Unknown Scenes Using DifferNet-Based Automatic Labeling Segmentation

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

1. The contribution is not very clear cut and needs to be rewritten.

2. In the method comparison section, most of the compared methods are before 2021, so the author can investigate this module again.

3. Would it be more expressive to use color in the visualization of Figure 3?

4. Experimental conditions and Settings can be more structured.

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Thank you very much for the valuable comments! Please find our reply to all reviewers in the attached file. Thanks!

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This study provides rigorous and rich outputs. It is considered a useful study for scientists working on obstacle detection. However, I would like to make some concerns about the paper:

- The article plan is missing at the end of chapter 1, please complete it.

- The sizes of the fonts used in the figures are different from each other. The image clarity in all figures should be improved and made publishable in the article.

- The authors have forgotten to cite the following IEEE reference conf. paper, which is given as follows:

http:/doi.org/10.1109/ISMSIT52890.2021.9604698

- The performance comparison is not solid. Would you please provide the previous achievements in the literature?

 

Author Response

Thank you very much for the valuable comments! Please find our reply to all reviewers in the attached file. Thanks!

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The article deals with the rather important direction of automatic labeling of images. 

The research is relevant and important, and the obtained results are valuable from a theoretical and practical point of view. Anyone who has manually labeled hundreds of images can attest to this.

Before publication, the article needs minor revision.

1. Please systematize the abstract according to generally accepted requirements. The abstract should be an objective representation of the article and gives a pertinent overview of the article and must contain the next structure: background, methods, results, conclusions. 

2. In addition, it is not customary to use references to literature sources in the abstract.

3. At the end of the Introduction section, I recommend that authors more clearly state the novelty and contribution of this study.

4. The discussion section is omitted. Authors need to prove the superiority of their research compared to previous ones.

Author Response

Thank you very much for the valuable comments! Please find our reply to all reviewers in the attached file. Thanks!

Author Response File: Author Response.pdf