Remote sensing small sample target detection method based on double-attention guided transfer learning

By constructing a content-aware strip pyramid network and a deformable attention region proposal network, the problems of multi-scale feature robustness and insufficient candidate region quality in remote sensing target detection with small sample sizes are solved, and high-precision remote sensing target detection is achieved.

CN121811250APending Publication Date: 2026-04-07ZHONGYUAN ENGINEERING COLLEGE
0 Cites 4 Cited by

Patent Information

Application Number
CN202512010800.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-29
Publication Date
2026-04-07

AI Technical Summary

Technical Problem

In existing remote sensing small sample target detection methods, feature pyramid networks lack content awareness, resulting in insufficient robustness of multi-scale features. Region proposal networks are unable to adapt to the geometric deformation of remote sensing targets, and the generated candidate region features are easily affected by background noise, leading to a decrease in classification accuracy and localization accuracy.

Method used

We employ a dual-attention-guided transfer learning approach to construct a content-aware strip pyramid network and a deformable attention region proposal network. We enhance multi-scale feature representation through content-aware upsampling and bidirectional strip convolution, and improve the accuracy of complex target localization by utilizing deformable convolution and spatial attention mechanisms.

Benefits of technology

It achieves long-range context awareness and adaptive fusion of multi-scale features, improving the detection accuracy and robustness of remote sensing target detection, and significantly enhancing detection performance under small sample conditions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention belongs to the technical field of computer vision and image processing, and discloses a remote sensing small sample target detection method based on double-attention guided transfer learning, and the method comprises the steps: obtaining a remote sensing image data set, and carrying out the preprocessing; taking the preprocessed remote sensing image training set as input, constructing a basic detection model by using a ResNet-101 backbone network, a feature pyramid network and a content awareness upsampling and regional proposal network, and obtaining basic model parameters; basic model parameters are used as input, a DA-FSDET network is trained based on a content awareness strip pyramid and a deformable attention area proposal network, and the trained DA-FSDET network is used to acquire a category detection frame containing small sample categories and confidence. Through cascading and cooperative work of the content awareness stripe pyramid and the deformable attention area proposal network, the detection precision and robustness of the multi-scale target in the remote sensing image are effectively improved.
Need to check novelty before this filing date? Find Prior Art