Darwinian Wiring: A Connectome-Constrained Structural Plasticity Framework for Extreme Model Compression.
Saved in:
| Title: | Darwinian Wiring: A Connectome-Constrained Structural Plasticity Framework for Extreme Model Compression. |
|---|---|
| Authors: | Tang, Lixing1,2 (AUTHOR), Zhong, Shaohong1,2 (AUTHOR), Gao, Wentao3 (AUTHOR), Liu, Jialang4 (AUTHOR), Xie, Yuhang5 (AUTHOR), Hu, Yaowen4,6 (AUTHOR), Ma, Wanqi1,6 (AUTHOR), Wei, Yingmei2,4 (AUTHOR), Guo, Yanming3,4 (AUTHOR) guoyanming@nudt.edu.cn |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 11, p1719. 32p. |
| Subjects: | Remote sensing, Power aware computing, Object recognition (Computer vision), Machine learning, Artificial neural networks, Functional connectivity |
| Abstract: | Highlights: What are the main findings? We propose the Darwinian Wiring framework which redefines lightweight detection as a dynamic adaptation process where the coupling of structural stability in the CAB and functional plasticity in the FCR enables high precision with minimal resources. We achieve breakthrough performance across multiple benchmarks: 79.57% mAP on DOTA v1.0 (82.35% under multi-scale settings), 98.62% mAP on HRSC2016, and 69.68% mAP on DIOR R, all while utilizing only 28.3 M parameters. What is the implication of the main finding? The CONERSLite framework provides a scalable, energy-efficient solution for oriented object detection on edge platforms by breaking the structural complexity and perceptual accuracy trade-off via instance-specific resource allocation. The deployment of lightweight object detectors on remote sensing edge platforms is severely constrained by the rigid trade-off between perception capacity and metabolic expenditure. To solve this fundamental challenge, we draw inspiration from the superior energy efficiency of the mammalian brain and the principles of connectomics to introduce CONERSLite. By emulating the dual mode synergy of biological neural systems, CONERSLite integrates a Compact Anatomical Backbone (CAB) representing the stable anatomical connectome and a Functional Connectome Router (FCR) that mimics the plasticity of the functional connectome. Our framework achieves a peak mAP of 82.35% on the DOTA-v1.0 dataset with only 28.3 M parameters and 195 G FLOPs, effectively establishing a new accuracy–efficiency Pareto frontier for remote sensing. On the HRSC2016 dataset, it reaches a state-of-the-art mAP of 98.62% while reducing the total parameter count by approximately 45% compared to high-precision optimized models like RTMDet. These results demonstrate that the application of connectomics principles provides a biologically grounded and highly efficient solution for resource-constrained remote sensing object detection. [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: 194586940 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Darwinian Wiring: A Connectome-Constrained Structural Plasticity Framework for Extreme Model Compression. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tang%2C+Lixing%22">Tang, Lixing</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhong%2C+Shaohong%22">Zhong, Shaohong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gao%2C+Wentao%22">Gao, Wentao</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Jialang%22">Liu, Jialang</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xie%2C+Yuhang%22">Xie, Yuhang</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hu%2C+Yaowen%22">Hu, Yaowen</searchLink><relatesTo>4,6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ma%2C+Wanqi%22">Ma, Wanqi</searchLink><relatesTo>1,6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wei%2C+Yingmei%22">Wei, Yingmei</searchLink><relatesTo>2,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Guo%2C+Yanming%22">Guo, Yanming</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<i> guoyanming@nudt.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jun2026, Vol. 18 Issue 11, p1719. 32p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Power+aware+computing%22">Power aware computing</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Functional+connectivity%22">Functional connectivity</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? We propose the Darwinian Wiring framework which redefines lightweight detection as a dynamic adaptation process where the coupling of structural stability in the CAB and functional plasticity in the FCR enables high precision with minimal resources. We achieve breakthrough performance across multiple benchmarks: 79.57% mAP on DOTA v1.0 (82.35% under multi-scale settings), 98.62% mAP on HRSC2016, and 69.68% mAP on DIOR R, all while utilizing only 28.3 M parameters. What is the implication of the main finding? The CONERSLite framework provides a scalable, energy-efficient solution for oriented object detection on edge platforms by breaking the structural complexity and perceptual accuracy trade-off via instance-specific resource allocation. The deployment of lightweight object detectors on remote sensing edge platforms is severely constrained by the rigid trade-off between perception capacity and metabolic expenditure. To solve this fundamental challenge, we draw inspiration from the superior energy efficiency of the mammalian brain and the principles of connectomics to introduce CONERSLite. By emulating the dual mode synergy of biological neural systems, CONERSLite integrates a Compact Anatomical Backbone (CAB) representing the stable anatomical connectome and a Functional Connectome Router (FCR) that mimics the plasticity of the functional connectome. Our framework achieves a peak mAP of 82.35% on the DOTA-v1.0 dataset with only 28.3 M parameters and 195 G FLOPs, effectively establishing a new accuracy–efficiency Pareto frontier for remote sensing. On the HRSC2016 dataset, it reaches a state-of-the-art mAP of 98.62% while reducing the total parameter count by approximately 45% compared to high-precision optimized models like RTMDet. These results demonstrate that the application of connectomics principles provides a biologically grounded and highly efficient solution for resource-constrained remote sensing object detection. [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=194586940 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18111719 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 32 StartPage: 1719 Subjects: – SubjectFull: Remote sensing Type: general – SubjectFull: Power aware computing Type: general – SubjectFull: Object recognition (Computer vision) Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Functional connectivity Type: general Titles: – TitleFull: Darwinian Wiring: A Connectome-Constrained Structural Plasticity Framework for Extreme Model Compression. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tang, Lixing – PersonEntity: Name: NameFull: Zhong, Shaohong – PersonEntity: Name: NameFull: Gao, Wentao – PersonEntity: Name: NameFull: Liu, Jialang – PersonEntity: Name: NameFull: Xie, Yuhang – PersonEntity: Name: NameFull: Hu, Yaowen – PersonEntity: Name: NameFull: Ma, Wanqi – PersonEntity: Name: NameFull: Wei, Yingmei – PersonEntity: Name: NameFull: Guo, Yanming IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 11 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
