HASO-DETR: hybrid attention small object detection based on RT-DETR

An improved RT-DETR algorithm for small-object detection in UAV aerial images

To address the challenges of UAV aerial imagery, including the prevalence of small objects, complex background interference, and difficulty in feature extraction that lead to high missed detection rates and compromise detection accuracy in existing RT-DETR algorithms, this paper proposes an improved small-object-oriented detector named MSFE-DETR (Multi-Scale Feature Enhancement DETR). A CMFE (CSP-MultiScale Feature Enhancement) module is integrated into the shallow backbone layers to enhance feature representation of small objects and alleviate feature loss caused by scale and background complexity. In deeper layers of backbone, the C2f module is employed to preserve fine-grained details and improve target–background discrimination, while multi-scale feature fusion further prevents small object information degradation. In addition, Deformable Attention (DAttention) is incorporated to adaptively focus on small target regions, retaining spatial positional information and suppressing background noise. The head integrates MPCA and FSA modules, where MPCA progressively fuses adjacent-scale features to complementarily enhance small object representations and suppress background interference, and FSA further improves detail enhancement and robustness. Moreover, an Inner-SIoU loss is proposed by combining Inner-IoU with SIoU, improving localization accuracy, convergence speed, and robustness in complex scenes. Experimental results on the VisDrone 2019 dataset show that MSFE-DETR outperforms RT-DETR-r18 by 1.9% in Precision, 2.1% in Recall and 2.4% in mAP@0.5, while real-time inference is maintained at 68.7 FPS. On the infrared HIT-UAV and satellite SIMD datasets, mAP@0.5 improves by 5.8% and 2.3% respectively over the baseline.

LE-YOLO: layered enhancement network for tiny object detection

Aiming at the challenges in small object detection in aerial images, such as extremely small object scales, weakened features, and background interference, this paper proposes a layered enhancement network named LE-YOLO. The proposed framework initiates enhancement at the feature level by integrating the DySample module, which replaces standard upsampling operators through a dynamic point sampling mechanism. This design significantly improves the reconstruction of fine-grained details with negligible computational overhead. Building upon this improved feature representation, a cross-layer feature fusion module is incorporated to aggregate multi-level features, effectively amplifying semantic coherence in regions of interest while suppressing extraneous background noise. Further refining the detection capability, the model introduces a layered enhancement head architecture. Within this head, a novel semantic information enhancement module employs multi-scale dilated convolutional layers to accommodate the substantial size variation characteristic of small aerial objects. The regression branch is subsequently optimized through receptive field adaptive convolutions, enhancing adaptability to diverse object scales. Complementing these architectural innovations, the training process utilizes the normalized Gaussian Wasserstein distance loss to diminish sensitivity to minor localization inaccuracies, particularly beneficial for small targets. Results demonstrate that compared to YOLOv8s, LE-YOLO improves AP50 by 3.1% and 1.7% on the AITOD and SIMD datasets, and outperforms other advanced models in comparative tests.

AS-YOLOR: An Improved YOLO Model for Small Object Detection in Aerial Images

An Adaptive and Scalable YOLO model named AS-YOLOR (Adaptive and Scalable YOLO for Rotated object detection), based on the YOLOv8 baseline is proposed, providing a solution with strong practical potential for achieving efficient and high-precision detection of small, rotated objects.

CDF-DETR: Cross-Stage Attention and Dual-Scale Feature Calibration for Small-Object Detection in UAV Remote Sensing Imagery

Small-object detection in unmanned aerial vehicle (UAV) remote sensing imagery is challenged by dense target distributions, substantial scale variation, complex ground backgrounds, and limited edge-computing resources. To address these challenges, we propose CDF-DETR, an end-to-end detector derived from the Real-Time Detection Transformer (RT-DETR). First, a Cross-Stage Partial Single-Head Attention Transformer (CSP-SHAT) backbone combines efficient local feature extraction with partial-channel global interaction to improve multi-scale representation while reducing the parameter count of the backbone. Second, a dual-scale feature calibration (DSFC) module sequentially performs contextual aggregation and deformable spatial alignment, thereby improving the consistency of shallow localization features and deep semantic features. Third, Focaler-MPDIoU integrates coordinate-sensitive regression with IoU-quality-based sample reweighting for dense small-object localization. Experiments on the VisDrone-2019 test set and the UAVDT and HIT-UAV validation sets demonstrate mAP50 improvements of 3.1, 1.4, and 3.0 percentage points, respectively, over the RT-DETR-R18 baseline. On the VisDrone-2019 validation set, CDF-DETR improves mAP50–95 from 26.20% to 28.52%, corresponding to a gain of 2.32 percentage points, while reducing the parameter count by 25.7%. A compressed INT8 variant achieves 20.84 FPS for an offline image-level pipeline on an NVIDIA Jetson Orin Nano using ONNX and TensorRT. These results demonstrate improved detection accuracy with a reduced parameter footprint for UAV remote sensing image analysis.

GS-DETR: Accurate and Efficient Object Detection in UAV Imagery with Gated Feature Fusion and an Enhanced Pyramid

DFA-Det: Dynamic Feature Augmentation and Hierarchical Adaptive Fusion for Small Object Detection in Low-Altitude Complex Scenes

Low-altitude unmanned-aerial-vehicle imagery exposes object detectors to a distinctive combination of tiny object footprints, dense instance layouts, abrupt scale variation, and weak texture under complex urban backgrounds. Existing detectors usually address these factors by adding larger backbones, denser feature pyramids, or heavier attention, but such independent additions often amplify background responses and dilute the fine localization cues needed by small targets. This paper proposes DFA-Det, a dynamic feature augmentation detector that treats low-altitude small-object detection as a coupled problem of context preservation, scale calibration, and content-aware refinement. The method first introduces a poly-kernel inception enhancement branch to preserve shallow structural details while expanding the effective receptive field. It then builds a Multi-Scale Interaction Encoder with Adaptive Feature Prior Learning and an Adaptive Feature Scaling Layer, where the latter contains a Bi-directional Channel Fusion Module that learns channel-wise evidence exchange between adjacent resolutions. Finally, a Hierarchical Refinement and Adaptive Fusion Module performs dynamic upsampling, semantic refinement, and adaptive fusion before the detection decoder. Experiments on the public VisDrone and CODrone benchmarks show that DFA-Det improves small-object precision, crowded-scene recall, and cross-scale robustness compared with representative two-stage, one-stage, transformer-based, and recent YOLO-family detectors. Extensive ablations, heatmaps, and qualitative comparisons indicate that the proposed modules cooperate as a coherent dynamic feature enhancement mechanism rather than isolated architectural attachments.