Multi-scale object detection in remote sensing imagery poses significant challenges, including substantial variations in object size, diverse orientations, and interference from complex backgrounds. To address these issues, we propose SADFF-Net, a novel detection framework that incorporates a Multi-scale Contextual Attention Fusion (MCAF) module to enhance information exchange between feature layers and suppress irrelevant feature interference. In addition, SADFF-Net employs an Adaptive Spatial Feature Fusion (ASFF) module to improve semantic consistency across feature layers by assigning spatial weights at multiple scales. To enhance adaptability to scale variations, the regression head integrates a deformable convolution. In contrast, the classification head utilizes depth-wise separable convolutions to significantly reduce computational complexity without compromising detection accuracy. Extensive experiments on the DOTAv1 and DIOR_R datasets demonstrate that SADFF-Net outperforms current state-of-the-art methods in multi-scale object detection.

Existing X-ray prohibited item detection methods primarily focus on boosting the detection performance of uniformly distributed items. However, in the real-world scenarios, various prohibited items exhibit the long-tailed distribution, thus posing the huge challenge to the detection task. To support this study, we introduce LTXRay, a dedicated X-ray benchmark that better assesses long-tailed prohibited item detection. LTXRay consists of 18,718 images from 12 common classes with an imbalance factor of 280.35. Meanwhile, we propose a novel Memory-Guided Learning Network(MGLNet) to develop baseline methods on LTXRay, which enhance the within-class diversity for the tail classes and consequentially improves long-tailed object detection. Specifically, we first introduce a frequency-based feature refinement module to extract discriminative contextual representations, then store the various instance features in the memory bank and dynamically generate the sample according to the historical features. Extensive experiments have been performed on the LTXRay to demonstrate the effectiveness of the proposed method. The experimental results indicate that the proposed method can consistently improve the performance of baseline methods.

Object detection is a fundamental challenge encountered in understanding and analyzing remote sensing images. Many current detection methods struggle to identify objects in remote sensing images due to poor feature saliency, diverse directions, and unique viewing angles of small remote sensing targets. As most remote sensing images are captured through overhead photography, the structural contour features of objects in these images remain relatively stable, such as the cross-shaped structure of the aircraft and the rectangular structure of the vehicle. Therefore, we utilize the physical simulation images as prior knowledge to supplement the invariant structural features of the target, extract the target’s key geometric features through the dynamic matching method, and fuse it with the features extracted by the neural network to detect the remote sensing small target more effectively in this article. We propose a template matching method based on physical simulation images (TMSI) and add it to the modified Darknet-53 (named TMSI-Net) for small target detection. Based on this, we perform specific transformations on existing templates in terms of target scale and direction to achieve better adaptation to the corresponding goals and propose DTMSI-Net with a dynamic template library (Dynamic TMSI-Net). Experiments on several datasets demonstrate that the DTMSI-Net exhibits higher detection accuracy and more stable performance compared with the state-of-the-art methods, 4% and 2.7% higher than the second-ranked model on the VEDAI and NWPU datasets, respectively.