Joint Classification of Hyperspectral and LiDAR Data Using Binary-Tree Transformer Network
, Bo Liu 2, Yanjun Wang 4 and Yuan Kou 5
Rakesh Chandra Vaishya
Round 1
Reviewer 1 Report
In this paper, the author proposed a novel binary-tree Transformer network, which is used to fuse heterogeneous information and utilize complementarity among multi-source remote sensing data to enhance the joint classification performance of hyperspectral image and LiDAR data. The experimental results demonstrate that the proposed network outperforms other networks in terms of accuracy. This study has important practical value in civil and military fields. But there are some details missing from the paper that are needed to make the paper complete for publication. Please make the following revisions:
1) On p 4 the authors mention “To better address issues such as inconsistent data structures, irrelevant physical properties, scarce training data, insufficient utilization of information, and imperfect feature fusion method, we propose an end-to-end neural network called BTRF-Net”.
- More details of the BTRF-Net neural network need to be described, such as how it addresses inconsistent data structures and compensates for the impact of data scarcity on results.
2) For the processing of hyperspectral data, it is necessary to consider factors such as background light signal and atmospheric attenuation. In this manuscript, how the author corrects these factors and more details need to be described. At the same time, the matching of elevation information and spectral information is also one of the key contents that needs to be emphasized.
3) On p 17 the authors mention “the multi-source transformer complementor (MSTC) utilizes the complementarity and cooperation among multimodal feature information in remote sensing images to better capture their correlation”.
- How it is implemented, more details need to be described.
4) Finally, the author state multiple sets of experiments were conducted to validate the effectiveness of our network on two datasets. But the author did not verify the accuracy and reliability of the transformer network method.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
May be
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
It's ok.
Reviewer 2 Report
Authors have revise the manuscript as per the reviewer comment.
Comments for author File: Comments.pdf
