GenericConv: A Generic Model for Image Scene Classification Using Few-Shot Learning
Round 1
Reviewer 1 Report
1.Where is the key word "MIT-indoor 67" reflected in the abstract?
2.The introduction lacks a summary of target detection and target classification.
3.The innovation were not elaborated. The author presents many research results, while research method is shown rarely. The innovation and key algorithm should be enhanced and elaborated detaily.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The paper proposes a learning model that tackles the scene classification challenge. Several machine learning models are used. Three datasets were tested.Good literature review. Good results visualization for each dataset.The authors present the mode as a combination of existing approaches.
However, a lot of questions should be presented better, namely:
1) The quality of Fig. 2- 3 is too low
2) Please explain in more detail the scientific novelty in Introduction
3) Please add the limitation and future work in Conclusions
4) How did the authors choose hyperparameters (Table 2)?
5) Please add information about datasets: are they balanced?
6) The link to the GitHub (line 305) doesn't work
7) The paper formatting and reference formatting are not appropriate.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The author have modified the manuscript according to the comments. I suggest accept the paper.
Reviewer 2 Report
Dear authors, thank you for your explanation. The paper looks better. Good luck
