PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery
Deep learning methods have achieved remarkable success in remote sensing object detection. Existing object detection methods focus on integrating convolutional neural networks (CNNs) and Transformer networks to explore local and global representations to improve performance. However, existing method...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/13/2213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849704587812929536 |
|---|---|
| author | Xiaofei Yang Suihua Xue Lin Li Sihuan Li Yudong Fang Xiaofeng Zhang Xiaohui Huang |
| author_facet | Xiaofei Yang Suihua Xue Lin Li Sihuan Li Yudong Fang Xiaofeng Zhang Xiaohui Huang |
| author_sort | Xiaofei Yang |
| collection | DOAJ |
| description | Deep learning methods have achieved remarkable success in remote sensing object detection. Existing object detection methods focus on integrating convolutional neural networks (CNNs) and Transformer networks to explore local and global representations to improve performance. However, existing methods relying on fixed convolutional kernels and dense global attention mechanisms suffer from computational redundancy and insufficient discriminative feature extraction, particularly for small and rotation-sensitive targets. To address these limitations, we propose a Dynamic Multi-Kernel Position-Aware Feature Pyramid Network (PAMFPN), which integrates adaptive sparse position modeling and multi-kernel dynamic fusion to achieve robust feature representation. Firstly, we design a position-interactive context module (PICM) that incorporates distance-aware sparse attention and dynamic positional encoding. It selectively focuses computation on sparse targets through a decay function that suppresses background noise while enhancing spatial correlations of critical regions. Secondly, we design a dual-kernel adaptive fusion (DKAF) architecture by combining region-sensitive attention (RSA) and reconfigurable context aggregation (RCA). RSA employs orthogonal large-kernel convolutions to capture anisotropic spatial features for arbitrarily oriented targets, while RCA dynamically adjusts the kernel scales based on content complexity, effectively addressing scale variations and intraclass diversity. Extensive experiments on three benchmark datasets (DOTA-v1.0, SSDD, HWPUVHR-10) demonstrate the effectiveness and versatility of the proposed PAMFPN. This work bridges the gap between efficient computation and robust feature fusion in remote sensing detection, offering a universal solution for real-world applications. |
| format | Article |
| id | doaj-art-d867090b826b43e6bee6a3304cf4ebcf |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-d867090b826b43e6bee6a3304cf4ebcf2025-08-20T03:16:42ZengMDPI AGRemote Sensing2072-42922025-06-011713221310.3390/rs17132213PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing ImageryXiaofei Yang0Suihua Xue1Lin Li2Sihuan Li3Yudong Fang4Xiaofeng Zhang5Xiaohui Huang6School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaBig Data Centre, Ministry of Emergency Management, Beijing 10110, ChinaShenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology (Shenzhen), Shenzhen 518055, ChinaSchool of Information Engineering, East China Jiaotong University, Nanchang 330000, ChinaDeep learning methods have achieved remarkable success in remote sensing object detection. Existing object detection methods focus on integrating convolutional neural networks (CNNs) and Transformer networks to explore local and global representations to improve performance. However, existing methods relying on fixed convolutional kernels and dense global attention mechanisms suffer from computational redundancy and insufficient discriminative feature extraction, particularly for small and rotation-sensitive targets. To address these limitations, we propose a Dynamic Multi-Kernel Position-Aware Feature Pyramid Network (PAMFPN), which integrates adaptive sparse position modeling and multi-kernel dynamic fusion to achieve robust feature representation. Firstly, we design a position-interactive context module (PICM) that incorporates distance-aware sparse attention and dynamic positional encoding. It selectively focuses computation on sparse targets through a decay function that suppresses background noise while enhancing spatial correlations of critical regions. Secondly, we design a dual-kernel adaptive fusion (DKAF) architecture by combining region-sensitive attention (RSA) and reconfigurable context aggregation (RCA). RSA employs orthogonal large-kernel convolutions to capture anisotropic spatial features for arbitrarily oriented targets, while RCA dynamically adjusts the kernel scales based on content complexity, effectively addressing scale variations and intraclass diversity. Extensive experiments on three benchmark datasets (DOTA-v1.0, SSDD, HWPUVHR-10) demonstrate the effectiveness and versatility of the proposed PAMFPN. This work bridges the gap between efficient computation and robust feature fusion in remote sensing detection, offering a universal solution for real-world applications.https://www.mdpi.com/2072-4292/17/13/2213deep learningobject detectionTransformerconvolution neural networkfeature fusion |
| spellingShingle | Xiaofei Yang Suihua Xue Lin Li Sihuan Li Yudong Fang Xiaofeng Zhang Xiaohui Huang PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery Remote Sensing deep learning object detection Transformer convolution neural network feature fusion |
| title | PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery |
| title_full | PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery |
| title_fullStr | PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery |
| title_full_unstemmed | PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery |
| title_short | PAMFPN: Position-Aware Multi-Kernel Feature Pyramid Network with Adaptive Sparse Attention for Robust Object Detection in Remote Sensing Imagery |
| title_sort | pamfpn position aware multi kernel feature pyramid network with adaptive sparse attention for robust object detection in remote sensing imagery |
| topic | deep learning object detection Transformer convolution neural network feature fusion |
| url | https://www.mdpi.com/2072-4292/17/13/2213 |
| work_keys_str_mv | AT xiaofeiyang pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery AT suihuaxue pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery AT linli pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery AT sihuanli pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery AT yudongfang pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery AT xiaofengzhang pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery AT xiaohuihuang pamfpnpositionawaremultikernelfeaturepyramidnetworkwithadaptivesparseattentionforrobustobjectdetectioninremotesensingimagery |