The widespread application of convolutional neural networks (CNNs) has led to significant advancements in object detection. However, challenges remain in achieving efficient and precise extraction of critical features when applying typical CNN-based methods to remote sensing detection tasks: (1) The convolutional kernels sliding horizontally in the backbone are misaligned with the features of arbitrarily oriented objects. Additionally, the detector shares the features extracted from the backbone, but the classification task requires orientation-invariant features while the regression task requires orientation-sensitive features. The inconsistency in feature requirements makes it difficult for the detector to extract the critical features required for each task. (2) The use of deeper convolutional structures can improve the detection accuracy, but it also results in substantial convolutional computations and feature redundancy, leading to inefficient feature extraction. To address this issue, we propose a Task-Sensitive Efficient Feature Extraction Network (TFE-Net). Specifically, we propose a special mixed fast convolution module for constructing an efficient network architecture that employs cheap transform operations to replace some of the convolution operations, generating more features with fewer parameters and computation resources. Next, we introduce the task-sensitive detection module, which first aligns the convolutional features with the targets using adaptive dynamic convolution based on the orientation of the targets. The task-sensitive feature decoupling mechanism is further designed to extract orientation-sensitive features and orientation-invariant features from the aligned features and feed them into the regression and classification branches, respectively, which provide the critical features needed for different tasks, thus improving the detection performance comprehensively. In addition, in order to make the training process more stable, we propose a balanced loss function to balance the gradients generated by different samples. Extensive experiments demonstrate that our proposed TFE-Net can achieve superior performance and obtain an effective balance between detection speed and accuracy on DOTA, UCAS-AOD, and HRSC2016.

In recent years, remote sensing object detection has witnessed significant advancements through deep explorations of convolutional neural networks (CNNs) and vision transformer (ViT) architectures. However, detecting rotated objects with high aspect ratios remains challenging. Current detection frameworks inadequately address the anisotropic feature distribution caused by such objects: feature information is highly concentrated in one spatial dimension while being sparse in another; and there are significant feature differences in the parameters representing the bounding box. To address this issue, we propose a Spatial Focusing and Progressive Decoupling Detector (SFPD-Det), which consists of three components: the Spatially Crosswise Convolution Module (SCCM), Hierarchical Decoupling Network (HDN), and Dynamic Progressive Activation Masks (DPMs). The SCCM captures diverse spatial features with long-range dependencies by combining square convolutions with multi-branch orthogonal large strip convolutions, enhancing the model adaptability to objects with varying aspect ratios. The HDN is composed of stacked ViT blocks and uses separate network branches to predict the position, angle, and size of bounding boxes in a cascaded manner. Furthermore, by combining the predicted parameters, we propose DPMs that embed the mask information of potential object boundary regions into the HDN, which progressively guide the self-attention to enhance cirtical features within the region of interest, thereby achieving precise bounding box regression. Extensive experiments on four benchmark remote sensing datasets (DOTA, DIOR-R, HRSC2016, and UCAS-AOD) demonstrate that our SFPD-Det achieves superior performance when compared with state-of-the-art detectors.

In recent years, detection methods for generic object detection have achieved significant progress. However, due to the large number of small objects in aerial images, mainstream detectors struggle to achieve a satisfactory detection performance. The challenges of small object detection in aerial images are primarily twofold: (1) Insufficient feature representation: The limited visual information for small objects makes it difficult for models to learn discriminative feature representations. (2) Background confusion: Abundant background information introduces more noise and interference, causing the features of small objects to easily be confused with the background. To address these issues, we propose a Multi-Level Contextual and Semantic Information Aggregation Network (MCSA-Net). MCSA-Net includes three key components: a Spatial-Aware Feature Selection Module (SAFM), a Multi-Level Joint Feature Pyramid Network (MJFPN), and an Attention-Enhanced Head (AEHead). The SAFM employs a sequence of dilated convolutions to extract multi-scale local context features and combines a spatial selection mechanism to adaptively merge these features, thereby obtaining the critical local context required for the objects, which enriches the feature representation of small objects. The MJFPN introduces multi-level connections and weighted fusion to fully leverage the spatial detail features of small objects in feature fusion and enhances the fused features further through a feature aggregation network. Finally, the AEHead is constructed by incorporating a sparse attention mechanism into the detection head. The sparse attention mechanism efficiently models long-range dependencies by computing the attention between the most relevant regions in the image while suppressing background interference, thereby enhancing the model’s ability to perceive targets and effectively improving the detection performance. Extensive experiments on four datasets, VisDrone, UAVDT, MS COCO, and DOTA, demonstrate that the proposed MCSA-Net achieves an excellent detection performance, particularly in small object detection, surpassing several state-of-the-art methods.