Open-Set Signal Recognition Based on Transformer and Wasserstein Distance
Round 1
Reviewer 1 Report
Please see the attached review report.
Comments for author File: 
Comments.pdf
Author Response
We thank the reviewer for carefully reading our revised manuscript and making valuable comments. Our detailed response has been attached.
Author Response File: Author Response.pdf
Reviewer 2 Report
The applications of the signal recognition should be described clearer.
The proposed algorithm should use a figure of block diagram to represent.
Some equation number is missing, e.g. page 8.
On page 10, the baseline methods need more descriptions. The statistical baseline methods should also be considered.
Please add more experiments and explanations. The improvement on the results so far is not very significant.
Author Response
We thank the reviewer for carefully reading our revised manuscript and making valuable comments. Our detailed response has been attached.
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper is sound with clearly emphasized contributions. It delas wit very interesting subject of recognising of unknown signals by an neural network. It is compared with state-of-the-art methods from the field and the obtained results clearly shows its advantage. My opinion is that the paper should be published.
Minor change:
1. I don't think that the term "a new evaluation criterion for verifying robustness"... "by introducing novel unknown signals", used in the abstract and introduction is appropriate. I would rather say that it is a new approach, than a new evaluation criterion.
Author Response
We thank the reviewer for carefully reading our revised manuscript and making valuable comments. Our detailed response has been attached.
Author Response File: Author Response.pdf
