Enhancing Dense Small Object Detection in UAV Images Based on HybridTransformer

Transformer-based models have facilitated significant advances in object detection. However, their extensive com-putational consumption and suboptimal detection of dense small objects curtail their applicability in unmannedaerial vehicle (UAV) imagery. Addressing these limitations, we propose a hybrid transformer-based detector, H-DETR, and enhance it for dense small objects, leading to an accurate and efficient model. Firstly, we introducea hybrid transformer encoder, which integrates a convolutional neural network-based cross-scale fusion modulewith the original encoder to handle multi-scale feature sequences more efficiently. Furthermore, we propose twonovel strategies to enhance detection performance without incurring additional inference computation. Queryfilter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similarqueries with a training-aware non-maximum suppression. Adversarial denoising learning is a novel enhancementmethod inspired by adversarial learning, which improves the detection of numerous small targets by counteractingthe effects of artificial spatial and semantic noise. Extensive experiments on the VisDrone and UAVDT datasetssubstantiate the effectiveness of our approach, achieving a significant improvement in accuracy with a reductionin computational complexity. Our method achieves 31.9% and 21.1% AP on the VisDrone and UAVDT datasets,respectively, and has a faster inference speed, making it a competitive model in UAV image object detection