GLFFNet: A Global and Local Features Fusion Network with Biencoder for Remote Sensing Image Segmentation

Round 1

Reviewer 1 Report

The paper is a study on the global and local features fusion network with biencoder for remote sensing image segmentation and is considered a valuable and interesting study in related fields. The reviewer's opinions are as follows.

 

1. In the section describing the simulations and experiments, the composition of the simulations and datasets should be clearly explained. It should be possible to solve the questions by the composition of the provided experimental environments including the models suggested and datasets provided. 

 

2. In the 'Conclusion' part, it is necessary to describe the limitations of the study and additional studies required in the future.

 

Thank you very much.

Throughout description, ambiguous expressions should be avoided and quantitative numerical values or objective grounds should be presented. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper is about the high-resolution remote sensing image segmentation using a combined algorithm based on deep learning concept.

The reason for this fusion is not well addressed in the introduction.

The innovation should be clearer in the introduction.

The abstract should be revised. It is written very vaguely and without introduction.

It is better to draw a graphical abstract for schematic structure of GLFFNet (Figure 1).

Maybe 1 dataset is not enough to test the proposed method. Diversity in the objects in the image is essential.

The proposed method has not achieved much higher accuracy than the previous methods. 1% better compared to UNetFormer! Is this an advantage? In addition, the complexity of the proposed method seems to be more than other methods.

Have you compared the methods in terms of performance speed?

The conclusion section should be expressed quantitatively around the results.

Average

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

The authors have done fabulous research in proposing a global and local feature fusion network with biencoder (GLFFNet) for high-resolution remote sensing image segmentation. . However, there are some aspects that need clarification and improvements.

1.     The motivation should be more cleared in Abstract.

2.     Table 5 and 6 should have number of references.

3.     The conclusion should be rewritten and included the drawbacks or challenging and future works.

4.     Furthermore, the manuscript has little grammatical mistakes, grammar and syntax issues need correction.

Minor editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The paper was revised well.

No