Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

By Chengcheng Wang, Wei He, Ying Nie, Jianyuan Guo, Chuanjian Liu, Kai Han, Yunhe Wang. Neural Information Processing Systems, 2023

614 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f289a75ec84a43dda3849118c04462f8629e1bf0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hongpeng Liao
2. Chien-Yao Wang
3. I-Hau Yeh
4. Zijia Lin
5. Guiguang Ding
6. Jungong Han
7. Hui Chen
8. Ao Wang

Citations in the corpus

• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception (2025, neutral): “Gold-YOLO [29] introduced a GD mechanism to enhance multi-scale feature fusion capabilities.”
• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (2024, methodology): “The current mainstream real-time object detectors are the YOLO series [2, 7, 13–15, 25, 30, 31, 47–49, 61–63, 74, 75], and most of these models use CSPNet [64] or ELAN [65] and their variants as the main computing units.”
• YOLOv10: Real-Time End-to-End Object Detection (2024, background): “For the neck, PAN [37], BiC [29], GD [60] and RepGFPN [71], etc ., are explored to enhance the multi-scale feature fusion.”
• Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation (2024, neutral): “Finally, we fuse and compress the semantic information of the three types of features through a concatenation operation followed by a 1 × 1 convolution to generate the X out with channel number 2 c , as follows:”
• YOLOv12: Attention-Centric Real-Time Object Detectors (2025, neutral): “The YOLO series [3, 9, 24, 28, 29, 32, 45–47, 53, 54, 57, 58] has emerged as a leading framework for real-time object detection.”