SaRPFF: A self-attention with register-based pyramid feature fusion module for enhanced rice leaf disease (RLD) detection.
Saved in:
| Title: | SaRPFF: A self-attention with register-based pyramid feature fusion module for enhanced rice leaf disease (RLD) detection. |
|---|---|
| Authors: | Haruna, Yunusa1 (AUTHOR) yunusa2k2@buaa.edu.cn, Qin, Shiyin1 (AUTHOR), Chukkol, Abdulrahman Hamman Adama2 (AUTHOR), Bello, Isah3 (AUTHOR), Lawan, Adamu1 (AUTHOR) |
| Source: | Multimedia Tools & Applications. Sep2025, Vol. 84 Issue 31, p38017-38043. 27p. |
| Subjects: | Rice diseases & pests, Object recognition (Computer vision), Computers in agriculture, Computer vision |
| Abstract: | Detecting objects across varying scales is still a challenge in computer vision, particularly in agricultural applications like Rice Leaf Disease (RLD) detection, where objects exhibit significant scale variations (SV). Conventional object detection (OD) like Faster R-CNN, SSD, and YOLO methods often fail to effectively address SV, leading to reduced accuracy and missed detections. To tackle this, we propose SaRPFF (Self-Attention with Register-based Pyramid Feature Fusion), a novel module designed to enhance multi-scale object detection. SaRPFF integrates 2D-Multi-Head Self-Attention (MHSA) with Register tokens, improving feature interpretability by mitigating artifacts within MHSA. Additionally, it integrates efficient attention atrous convolutions into the pyramid feature fusion and introduce a deconvolutional layer for refined up-sampling. We evaluate SaRPFF on YOLOv7 using the MRLD and COCO datasets. Our approach demonstrates a + 2.61 % improvement in Average Precision (AP) on the MRLD dataset compared to the baseline FPN method in YOLOv7. Furthermore, SaRPFF outperforms other FPN variants, including BiFPN, NAS-FPN, and PANET, showcasing its versatility and potential to advance OD techniques. This study highlights SaRPFF effectiveness in addressing SV challenges and its adaptability across FPN-based OD models. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 188021242 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: SaRPFF: A self-attention with register-based pyramid feature fusion module for enhanced rice leaf disease (RLD) detection. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Haruna%2C+Yunusa%22">Haruna, Yunusa</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yunusa2k2@buaa.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Qin%2C+Shiyin%22">Qin, Shiyin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chukkol%2C+Abdulrahman+Hamman+Adama%22">Chukkol, Abdulrahman Hamman Adama</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bello%2C+Isah%22">Bello, Isah</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lawan%2C+Adamu%22">Lawan, Adamu</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Multimedia+Tools+%26+Applications%22">Multimedia Tools & Applications</searchLink>. Sep2025, Vol. 84 Issue 31, p38017-38043. 27p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Rice+diseases+%26+pests%22">Rice diseases & pests</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Computers+in+agriculture%22">Computers in agriculture</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Detecting objects across varying scales is still a challenge in computer vision, particularly in agricultural applications like Rice Leaf Disease (RLD) detection, where objects exhibit significant scale variations (SV). Conventional object detection (OD) like Faster R-CNN, SSD, and YOLO methods often fail to effectively address SV, leading to reduced accuracy and missed detections. To tackle this, we propose SaRPFF (Self-Attention with Register-based Pyramid Feature Fusion), a novel module designed to enhance multi-scale object detection. SaRPFF integrates 2D-Multi-Head Self-Attention (MHSA) with Register tokens, improving feature interpretability by mitigating artifacts within MHSA. Additionally, it integrates efficient attention atrous convolutions into the pyramid feature fusion and introduce a deconvolutional layer for refined up-sampling. We evaluate SaRPFF on YOLOv7 using the MRLD and COCO datasets. Our approach demonstrates a + 2.61 % improvement in Average Precision (AP) on the MRLD dataset compared to the baseline FPN method in YOLOv7. Furthermore, SaRPFF outperforms other FPN variants, including BiFPN, NAS-FPN, and PANET, showcasing its versatility and potential to advance OD techniques. This study highlights SaRPFF effectiveness in addressing SV challenges and its adaptability across FPN-based OD models. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=188021242 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11042-025-20696-3 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 27 StartPage: 38017 Subjects: – SubjectFull: Rice diseases & pests Type: general – SubjectFull: Object recognition (Computer vision) Type: general – SubjectFull: Computers in agriculture Type: general – SubjectFull: Computer vision Type: general Titles: – TitleFull: SaRPFF: A self-attention with register-based pyramid feature fusion module for enhanced rice leaf disease (RLD) detection. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Haruna, Yunusa – PersonEntity: Name: NameFull: Qin, Shiyin – PersonEntity: Name: NameFull: Chukkol, Abdulrahman Hamman Adama – PersonEntity: Name: NameFull: Bello, Isah – PersonEntity: Name: NameFull: Lawan, Adamu IsPartOfRelationships: – BibEntity: Dates: – D: 25 M: 09 Text: Sep2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 13807501 Numbering: – Type: volume Value: 84 – Type: issue Value: 31 Titles: – TitleFull: Multimedia Tools & Applications Type: main |
| ResultId | 1 |
