Global Edge Information Guidance With Polarity-Aware Attention for Satellite Object Detection

Object detection in remote sensing imagery remains challenging due to extreme-scale variations and deployment computational inefficiency. Existing Transformer-based detectors exhibit incomplete feature representations stemming from limited scale-awareness in handling multiscale objects, insufficient modeling of negative-polarity interactions, and uniform attention distributions. To address these limitations, this article proposes a novel framework integrating a global edge information extraction (GEIE) module and polarity-aware linear attention-based internal feature interaction (PLAIFI) module. The GEIE module consists of two components to integrate multiscale edge features: a polyresolution edge feature producer (PREFP) module and an edge fusion module. The PREFP module extracts edge information using a 3-D SobelConv branch applied to shallow features and generates a multiscale feature map to augment the hybrid encoder’s multiscale representations with edge-aware priors. The edge fusion module supports flexible integration to enrich boundary-aware representations. To establish complementary feature enhancement, the PLAIFI module decomposes query–key pairs into positive-/negative-polarity components via learnable projection matrices, explicitly models same- and opposite-signed interactions through dual-polarity branches with polarity-sensitive coefficient matrices, and employs channelwise learnable power functions to sharpen attention distributions by reducing entropy—enhancing scale-awareness while maintaining linear complexity. Extensive experiments demonstrate state-of-the-art performance: 95.0% mean average precision (mAP) (+4.6%) on HRSC2016 (small-scale ships), 73.0% mAP (+5.9%) on DOTAv1.5 (multiclass objects), and 93.9% mAP on SIRSTv2 (tiny-scale infrared targets), achieved with 11.4% giga floating-point operations per second (GFLOPs)/11% Params increase over baseline real-time detection Transformer (RT-DETR). The principal innovation constitutes a synergistic framework where edge-aware feature recalibration and polarity-driven attention refinement mutually reinforce each other, establishing new state-of-the-art performance while maintaining deployment-friendly computational efficiency on satellite imagery. The source code will be available at: https://github.com/Keykeykeykeykeykey/Global_Edge_Guidance