A CNNA-Based Lightweight Multi-Scale Tomato Pest and Disease Classification Method
Round 1
Reviewer 1 Report
see the attachment
Comments for author File: 
Comments.pdf
Moderate editing of English language
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
In this paper, a lightweight multi-scale tomato pest classification network is proposed, and a multi-scale feature fusion module is proposed to improve the feature extraction ability of the model, and global channel attention is proposed to improve the sensitivity of the network model. At the same time, global channel attention is proposed to improve the sensitivity of the network model. The identification of pests and diseases during tomato growth was optimized. Technical support can be provided for the post-management and development of control systems for tomato pests.
1. The reflection phenomenon in Figure 1c is serious, which brings a bad look and feel to the reader, and it is recommended to replace it. Figure 1d is too vague.
2. As described in lines 139-141, the original sample is then rotated 40 degrees and rotated horizontally, whether it is processed on a two-dimensional picture computer, and if so, please briefly describe the implementation process.
3. 2.4 Whether hardware devices and environmental configurations should be described in advance.
4. The actual application scenario is not clearly reflected in the text, please briefly describe it.
Appropriate modifications are required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The author has incorporated all the comments.
Minor editing of English language required
Author Response
On behalf of all authors, I would like to express our thanks for giving us an opportunity to revise our manuscript, and we greatly appreciate the editor and reviewers for their positive and constructive comments and suggestions on our manuscript entitled “A CNNA-based lightweight multi-scale tomato pest and disease classification method”. (ID: 2379708).
We carefully studied the reviewers' comments and revised and polished the English language of the paper accordingly, while also utilizing the "Track Changes" function. Please see the manuscript for details.
Finally, we hope that the paper now meets the high standard of the journal and looking forward to hearing from you soon.
Best regards,
Zhiyuan Gao
Email: [email protected]
Yanlei Xu
Email: [email protected]
College of Information and Technology, JiLin Agricultural University, Changchun 130118, China.
