In the past years, YOLO-series models have emerged as the leading approaches in the area of real-time object detection. Many studies pushed up the baseline to a higher level by modifying the architecture, augmenting data and designing new losses. However, we find previous models still suffer from information fusion problem, although Feature Pyramid Network (FPN) and Path Aggregation Network (PANet) have alleviated this. Therefore, this study provides an advanced Gatherand-Distribute mechanism (GD) mechanism, which is realized with convolution and self-attention operations. This new designed model named as Gold-YOLO, which boosts the multi-scale feature fusion capabilities and achieves an ideal balance between latency and accuracy across all model scales. Additionally, we implement MAE-style pretraining in the YOLO-series for the first time, allowing YOLOseries models could be to benefit from unsupervised pretraining. Gold-YOLO-N attains an outstanding 39.9% AP on the COCO val2017 datasets and 1030 FPS on a T4 GPU, which outperforms the previous SOTA model YOLOv6-3.0-N with similar FPS by +2.4%. The PyTorch code is available at https://github.com/huawei-noah/Efficient-Computing/tree/master/Detection/Gold-YOLO, and the MindSpore code is available at https://gitee.com/mindspore/models/tree/master/research/cv/Gold_YOLO.

翻译：近年来，YOLO系列模型已成为实时目标检测领域的领先方法。众多研究通过改进架构、数据增强和设计新损失函数不断推高基线性能。然而，我们发现现有模型仍存在信息融合问题——尽管特征金字塔网络（FPN）和路径聚合网络（PANet）已在一定程度上缓解该问题。为此，本研究提出一种先进的收集-分发机制（GD机制），通过卷积与自注意力操作实现。基于该机制设计的新型模型命名为Gold-YOLO，它显著增强了多尺度特征融合能力，并在所有模型尺度上实现了延迟与精度的理想平衡。此外，我们在YOLO系列中首次引入MAE式预训练，使YOLO系列模型能够受益于无监督预训练。Gold-YOLO-N在COCO val2017数据集上取得39.9% AP的卓越性能，并在T4 GPU上达到1030 FPS，相比FPS相近的先前最先进模型YOLOv6-3.0-N提升了2.4%。PyTorch代码见 https://github.com/huawei-noah/Efficient-Computing/tree/master/Detection/Gold-YOLO，MindSpore代码见 https://gitee.com/mindspore/models/tree/master/research/cv/Gold_YOLO。