Research on Seamless Fabric Defect Detection Based on Improved YOLOv8n
Round 1
Reviewer 1 Report
Comments and Suggestions for Authorshe paper proposes an improved YOLOv8n model for seamless fabric defect detection, which claims performance enhancements through modules like SPPF_LSKA and CARAFE upsampling. However, the references are notably shallow, and the comparative analysis is lacking in depth. The authors compare their model only against previous YOLO versions, which is insufficient.
They fail to reference key studies like the comprehensive survey by Chao Li et al. (2021), “Fabric Defect Detection in Textile Manufacturing: A Survey of the State of the Art.” In Table 6 of this survey, multiple deep learning-based methods for fabric defect detection are outlined, providing a broader context for comparison. The omission of such critical references diminishes the strength of the presented comparisons. A more robust evaluation, including a comparison with other state-of-the-art methods beyond YOLO, would significantly enhance the paper’s contribution.
Author Response
Please see the attachment
Author Response File: Author Response.docx
Reviewer 2 Report
Comments and Suggestions for Authors1. In abstract need to focus more about method novelness.
2. The related work section is extensive, but a critical comparison table summarizing the methods, key improvements, and limitations of previous works versus the proposed method would be very helpful.
3. Discuss limitations of prior research more explicitly, highlighting the motivation for your improvements.
4. For the CARAFE module, present an ablative comparison with other interpolation methods such as bilinear, bicubic, nearest neighbor.
5. Why was an 8:1:1 train-test-validation split used? Was this empirically determined to be optimal?
6. Some sentences are overly long and technical. Simplifying certain complex sentences can improve readability.
7. Minor grammatical issues for example “making it difficult to balance real-time performance and precision” → “making it challenging to balance real-time performance with precision”.
Author Response
Please see the attachment
Author Response File: Author Response.docx
Reviewer 3 Report
Comments and Suggestions for AuthorsThe article is relevant and can be published
Comments for author File: Comments.pdf
Author Response
Please see the attachment
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThe comments I have posed are now ok
Reviewer 2 Report
Comments and Suggestions for AuthorsManuscript improved a lot