Next Article in Journal
Electrospray Nested Energetic Cells from Nanothermite with MoO3 Nanostrips: Reactivity, Sensitivity and Combustion Performance
Previous Article in Journal
Effects of La-Co Co-Substitution and Magnetic Field Pressing on the Structural and Magnetic Properties of SrM Hexaferrites
Previous Article in Special Issue
Remote Sensing Applications in Almond Orchards: A Comprehensive Systematic Review of Current Insights, Research Gaps, and Future Prospects
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 14
Issue 13
10.3390/app14135520
Review Report
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Intelligently Counting Agricultural Pests by Integrating SAM with FamNet

Appl. Sci. 2024, 14(13), 5520; https://doi.org/10.3390/app14135520
by Jiajun Qing 1, Xiaoling Deng 1,2,3,*, Yubin Lan 1,2,3 and Jidong Xian 1,2,3
Reviewer 1:
Andres Gallego
Reviewer 2: Anonymous
Appl. Sci. 2024, 14(13), 5520; https://doi.org/10.3390/app14135520
Submission received: 20 March 2024 / Revised: 2 June 2024 / Accepted: 5 June 2024 / Published: 25 June 2024
(This article belongs to the Special Issue Machine Vision and Hyperspectral Imaging Technologies and Applications for the Agri-Food Sector)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper accurately describes how a TopK matching algorithm to propagate accurate labels and the forgetting mechanism can significantly improve the FamNet baseline model.

The dataset, however, includes the description of the images but the authors do not specify why these conditions were chosen. For example, in section 2.1, the authors state "Images of citrus psyllids under different natural light intensities were captured during three time periods: 9:00-11:00, 14:00-15:00, and 17:00-18:00 every day.". Does this represent good or bad conditions?

 

The proposal of a system called Segment Assist in Count (SAM) for counting with the assistance of FamNet for a small dataset of RGB images is interesting. Also, the authos bring valuable insights on how the system can be improved and its limitations. 

 

Comments on the Quality of English Language

I suggest a minor english revision to make the text more readable, but it can be published as is.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

1. The introduction section needs to be refined. For example, the 4th to 8th sentences in Paragraph 1 talk about relevant studies on counting pests, which should be placed in Paragraph 3. "Subsequently" in Paragraph looks odd as the Ferentinos paper was published in 2018 after the Li paper. Paragraph 4 also appears abruptly - it is better to add one sentence explaining why large language models are relevant. The citation for "Can sam count anything?" should be placed just at the end of the sentence. 

2. "Count Every Thing" model is used interchangeably with FamNet in both text and figures without a clear explanation. It is better to use a consistent term or add a sentence to explain this.

3. How do you determine the value of K in TopK tag matching? This is not clearly discussed in the manuscript.

4. "Figure 1" at the end of Paragraph 2 in Section 2.1 is probably "Figure 2" - please confirm. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop