Timezone: »

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism
Chengcheng Wang · Wei He · Ying Nie · Jianyuan Guo · Chuanjian Liu · Yunhe Wang · Kai Han

Thu Dec 14 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #219

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.

Author Information

Chengcheng Wang (Huawei Technologies Ltd.)
Wei He
Ying Nie (Huawei Technologies Ltd.)
Jianyuan Guo (University of Sydney)
Chuanjian Liu (Huawei Noah's Ark Lab)
Yunhe Wang (Huawei Noah's Ark Lab)
Kai Han (Huawei Noah's Ark Lab)

More from the Same Authors