Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification

Round 1

Reviewer 1 Report

The paper is interesting and the results are quite impressive.

It would be interesting to see how the method performs on a scene with a large number of mixed pixels e.g. Cuprite.

With each experiment you comment that the results from WSWS "are much smoother," but this is not so obvious. Perhaps you could direct the readers attention to a few locations where this is clear. E.g. "see for example the region around..." (or mark out the region) in comparison with...

The manuscript would benefit from further proofreading, particularly in the introduction.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear authors,

Thank you very much for this interesseting paper about wide sliding window and subsampling Network for HSI Classification.

Nevertheless I have some points:

1. Abstract has to be improved. Especially, the structure.
2. Introduction has to be improved. Maybe some points can be summarized in a table. Citations of Reviews in the beginning of the paper.
3. Discussion: Not all results/experiments are discussed.
4. Expression has to be improved. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper is well-written for publication in MDPI Remote Sensing. However, I recommended the authors to include the total time taken for each algorithm below the respective tables. This recommendation is because datasets like Pavia and KSC have a handful of pixels when compared with AVIRIS or some of the images that come out of HySpex sensors. Those images contain millions (sometimes billions) of pixels, and the scalability of the proposed method can be tested with other algorithms like DOI:10.1016/j.neucom.2020.04.138 and 10.1016/j.patcog.2020.107298.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf