A Unified Framework with Dynamic Kernel Learning for Bidirectional Feature Resampling in Remote Sensing Images.
Saved in:
| Title: | A Unified Framework with Dynamic Kernel Learning for Bidirectional Feature Resampling in Remote Sensing Images. |
|---|---|
| Authors: | Xiang, Jiajun1 (AUTHOR), Xiao, Zixuan1 (AUTHOR), Wang, Shuojie1 (AUTHOR), Fu, Ruigang1 (AUTHOR) furuigang08@nudt.edu.cn, Zhong, Ping1 (AUTHOR) |
| Source: | Remote Sensing. Nov2025, Vol. 17 Issue 21, p3599. 21p. |
| Subjects: | Remote-sensing images, Resampling (Statistics), Parameterization, Object recognition (Computer vision), Interpolation, Feature extraction |
| Abstract: | Highlights: What are the main findings? A lightweight dynamic resampling kernel based on a compact source space and bilinear interpolation achieves competitive performance with significantly fewer parameters, eliminating the need for learnable offsets and channel compression. A unified bidirectional resampling framework ensures architectural consistency across upsampling and downsampling operations, enhancing multiscale feature learning for remote sensing object detection. Extensive validation on DIOR and DOTA benchmarks shows consistent performance improvements over baseline methods under substantially reduced parameter constraints. What is the implication of the main finding? The method provides a highly parameter-efficient alternative to existing learnable resamplers, making it suitable for resource-constrained deployment scenarios. The unified design facilitates more coherent feature representation learning across scales, which is essential for accurate detection in complex remote sensing imagery. The inherent multiscale nature of objects poses a fundamental challenge in remote sensing object detection. To address this, feature pyramids have been widely adopted as a key architectural component. However, the effectiveness of these pyramids critically depends on the sampling operations used to construct them, highlighting the need to move beyond traditional fixed-kernel methods. While conventional interpolation approaches (e.g., nearest-neighbor and bilinear) are computationally efficient, their content-agnostic nature often leads to detail loss and artifacts. Recent dynamic sampling operators improve performance through content-aware mechanisms, yet they typically incur substantial computational and parametric costs, hindering their applicability in resource-constrained scenarios. To overcome these limitations, we propose Lurker, a learned and unified resampling kernel that supports both upsampling and downsampling within a consistent framework. Lurker constructs a compact source kernel space and employs bilinear interpolation to generate adaptive kernels, enabling content-aware feature reassembly while maintaining a lightweight parameter footprint. Extensive experiments on the DIOR and DOTA datasets demonstrate that Lurker achieves a favorable trade-off between detection accuracy and efficiency, outperforming existing resampling methods in terms of both accuracy and parameter efficiency, making it especially suitable for remote sensing object detection applications. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI 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: 189611941 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A Unified Framework with Dynamic Kernel Learning for Bidirectional Feature Resampling in Remote Sensing Images. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Xiang%2C+Jiajun%22">Xiang, Jiajun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xiao%2C+Zixuan%22">Xiao, Zixuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Shuojie%22">Wang, Shuojie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Fu%2C+Ruigang%22">Fu, Ruigang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> furuigang08@nudt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhong%2C+Ping%22">Zhong, Ping</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Nov2025, Vol. 17 Issue 21, p3599. 21p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Remote-sensing+images%22">Remote-sensing images</searchLink><br /><searchLink fieldCode="DE" term="%22Resampling+%28Statistics%29%22">Resampling (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Parameterization%22">Parameterization</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Interpolation%22">Interpolation</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? A lightweight dynamic resampling kernel based on a compact source space and bilinear interpolation achieves competitive performance with significantly fewer parameters, eliminating the need for learnable offsets and channel compression. A unified bidirectional resampling framework ensures architectural consistency across upsampling and downsampling operations, enhancing multiscale feature learning for remote sensing object detection. Extensive validation on DIOR and DOTA benchmarks shows consistent performance improvements over baseline methods under substantially reduced parameter constraints. What is the implication of the main finding? The method provides a highly parameter-efficient alternative to existing learnable resamplers, making it suitable for resource-constrained deployment scenarios. The unified design facilitates more coherent feature representation learning across scales, which is essential for accurate detection in complex remote sensing imagery. The inherent multiscale nature of objects poses a fundamental challenge in remote sensing object detection. To address this, feature pyramids have been widely adopted as a key architectural component. However, the effectiveness of these pyramids critically depends on the sampling operations used to construct them, highlighting the need to move beyond traditional fixed-kernel methods. While conventional interpolation approaches (e.g., nearest-neighbor and bilinear) are computationally efficient, their content-agnostic nature often leads to detail loss and artifacts. Recent dynamic sampling operators improve performance through content-aware mechanisms, yet they typically incur substantial computational and parametric costs, hindering their applicability in resource-constrained scenarios. To overcome these limitations, we propose Lurker, a learned and unified resampling kernel that supports both upsampling and downsampling within a consistent framework. Lurker constructs a compact source kernel space and employs bilinear interpolation to generate adaptive kernels, enabling content-aware feature reassembly while maintaining a lightweight parameter footprint. Extensive experiments on the DIOR and DOTA datasets demonstrate that Lurker achieves a favorable trade-off between detection accuracy and efficiency, outperforming existing resampling methods in terms of both accuracy and parameter efficiency, making it especially suitable for remote sensing object detection applications. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI 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=189611941 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs17213599 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 3599 Subjects: – SubjectFull: Remote-sensing images Type: general – SubjectFull: Resampling (Statistics) Type: general – SubjectFull: Parameterization Type: general – SubjectFull: Object recognition (Computer vision) Type: general – SubjectFull: Interpolation Type: general – SubjectFull: Feature extraction Type: general Titles: – TitleFull: A Unified Framework with Dynamic Kernel Learning for Bidirectional Feature Resampling in Remote Sensing Images. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Xiang, Jiajun – PersonEntity: Name: NameFull: Xiao, Zixuan – PersonEntity: Name: NameFull: Wang, Shuojie – PersonEntity: Name: NameFull: Fu, Ruigang – PersonEntity: Name: NameFull: Zhong, Ping IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 11 Text: Nov2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 17 – Type: issue Value: 21 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
