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
this https URL, and the
MindSpore code is available at
this https URL

在本研究中，我们提出了一种先进的 Gatherand-Distribute 机制（GD 机制），该机制借助卷积和自注意操作实现。我们设计的新模型 Gold-YOLO 在跨所有模型尺度上提升了多尺度特征融合能力并在延迟和准确性之间实现了理想的平衡。此外，我们首次在 YOLO 系列中实现了 MAE 风格的预训练，使得 YOLO 系列模型能够从无监督预训练中受益。Gold-YOLO-N 在 COCO val2017 数据集上取得了出色的 39.9％ AP 和在 T4 GPU 上的 1030 FPS，超过了以前的 SOTA 模型 YOLOv6-3.0-N 的相似 FPS +2.4％。