Bi-Directional Pyramid Network for Edge Detection
Round 1
Reviewer 1 Report
Kindly refer to the attachment
Comments for author File: 
Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
The authors propose a novel multi-scale learning method for edge detection. The method is based on a bi-directional pyramid network, which is formed by down- and lightweight up-sampling pyramid networks combined with a trimmed VGG16 backbone. The presented results of the comparative analysis show that the proposed method can be a trade-off between the state-of-the-art BDCN and RCF from the training speed and accuracy.
The paper is well-structured and could be of interest to the audience in the field of neurocomputing. The readability of the paper can be improved by the following.
The authors leave without introduction the acronyms they refer to, please use the full terms for the first time in the text.
The manuscript is completely devoid of formulas. Please provide formal definitions at least for the utilized metrics: precision and recall, ODS, OIS, AP.
I also recommend minor spell and grammar checking, in particular the use of indefinite articles.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors have addressed majority of the comments, successfully. The papers needs to be checked for Minor English Language correction.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
