@ -19,12 +19,13 @@ Here are some of the key models supported:
5. **[YOLOv7](yolov7.md)**: Updated YOLO models released in 2022 by the authors of YOLOv4.
5. **[YOLOv7](yolov7.md)**: Updated YOLO models released in 2022 by the authors of YOLOv4.
6. **[YOLOv8](yolov8.md) NEW 🚀**: The latest version of the YOLO family, featuring enhanced capabilities such as instance segmentation, pose/keypoints estimation, and classification.
6. **[YOLOv8](yolov8.md) NEW 🚀**: The latest version of the YOLO family, featuring enhanced capabilities such as instance segmentation, pose/keypoints estimation, and classification.
7. **[YOLOv9](yolov9.md)**: An experimental model trained on the Ultralytics [YOLOv5](yolov5.md) codebase implementing Programmable Gradient Information (PGI).
7. **[YOLOv9](yolov9.md)**: An experimental model trained on the Ultralytics [YOLOv5](yolov5.md) codebase implementing Programmable Gradient Information (PGI).
8. **[Segment Anything Model (SAM)](sam.md)**: Meta's Segment Anything Model (SAM).
8. **[YOLOv10](yolov10.md)**: By Tsinghua University, featuring NMS-free training and efficiency-accuracy driven architecture, delivering state-of-the-art performance and latency.
9. **[Mobile Segment Anything Model (MobileSAM)](mobile-sam.md)**: MobileSAM for mobile applications, by Kyung Hee University.
9. **[Segment Anything Model (SAM)](sam.md)**: Meta's Segment Anything Model (SAM).
10. **[Fast Segment Anything Model (FastSAM)](fast-sam.md)**: FastSAM by Image & Video Analysis Group, Institute of Automation, Chinese Academy of Sciences.
10. **[Mobile Segment Anything Model (MobileSAM)](mobile-sam.md)**: MobileSAM for mobile applications, by Kyung Hee University.
11. **[Fast Segment Anything Model (FastSAM)](fast-sam.md)**: FastSAM by Image & Video Analysis Group, Institute of Automation, Chinese Academy of Sciences.
YOLOv10, built on the [Ultralytics](https://ultralytics.com) [Python package](https://pypi.org/project/ultralytics/) by researchers at [Tsinghua University](https://www.tsinghua.edu.cn/en/), introduces a new approach to real-time object detection, addressing both the post-processing and model architecture deficiencies found in previous YOLO versions. By eliminating non-maximum suppression (NMS) and optimizing various model components, YOLOv10 achieves state-of-the-art performance with significantly reduced computational overhead. Extensive experiments demonstrate its superior accuracy-latency trade-offs across multiple model scales.
YOLOv10 will be integrated into the Ultralytics library as quickly as possible. Make sure to follow us on all social media channels and follow our [GitHub repository](https://github.com/ultralytics/ultralytics) for updates 🚀
YOLOv10 introduces a new approach to real-time object detection, addressing both the post-processing and model architecture deficiencies found in previous YOLO versions. By eliminating non-maximum suppression (NMS) and optimizing various model components, YOLOv10 achieves state-of-the-art performance with significantly reduced computational overhead. Extensive experiments demonstrate its superior accuracy-latency trade-offs across multiple model scales.
## Overview
## Overview
Real-time object detection aims to accurately predict object categories and positions in images with low latency. The YOLO series has been at the forefront of this research due to its balance between performance and efficiency. However, reliance on NMS and architectural inefficiencies have hindered optimal performance. YOLOv10 addresses these issues by introducing consistent dual assignments for NMS-free training and a holistic efficiency-accuracy driven model design strategy.
Real-time object detection aims to accurately predict object categories and positions in images with low latency. The YOLO series has been at the forefront of this research due to its balance between performance and efficiency. However, reliance on NMS and architectural inefficiencies have hindered optimal performance. YOLOv10 addresses these issues by introducing consistent dual assignments for NMS-free training and a holistic efficiency-accuracy driven model design strategy.
### Architecture
The architecture of YOLOv10 builds upon the strengths of previous YOLO models while introducing several key innovations. The model architecture consists of the following components:
1. **Backbone**: Responsible for feature extraction, the backbone in YOLOv10 uses an enhanced version of CSPNet (Cross Stage Partial Network) to improve gradient flow and reduce computational redundancy.
2. **Neck**: The neck is designed to aggregate features from different scales and passes them to the head. It includes PAN (Path Aggregation Network) layers for effective multiscale feature fusion.
3. **One-to-Many Head**: Generates multiple predictions per object during training to provide rich supervisory signals and improve learning accuracy.
4. **One-to-One Head**: Generates a single best prediction per object during inference to eliminate the need for NMS, thereby reducing latency and improving efficiency.
## Key Features
## Key Features
1. **NMS-Free Training**: Utilizes consistent dual assignments to eliminate the need for NMS, reducing inference latency.
1. **NMS-Free Training**: Utilizes consistent dual assignments to eliminate the need for NMS, reducing inference latency.
@ -39,6 +44,17 @@ YOLOv10 comes in various model scales to cater to different application needs:
YOLOv10 outperforms previous YOLO versions and other state-of-the-art models in terms of accuracy and efficiency. For example, YOLOv10-S is 1.8x faster than RT-DETR-R18 with similar AP on the COCO dataset, and YOLOv10-B has 46% less latency and 25% fewer parameters than YOLOv9-C with the same performance.
YOLOv10 outperforms previous YOLO versions and other state-of-the-art models in terms of accuracy and efficiency. For example, YOLOv10-S is 1.8x faster than RT-DETR-R18 with similar AP on the COCO dataset, and YOLOv10-B has 46% less latency and 25% fewer parameters than YOLOv9-C with the same performance.
YOLOv10 has been extensively tested on standard benchmarks like COCO, demonstrating superior performance and efficiency. The model achieves state-of-the-art results across different variants, showcasing significant improvements in latency and accuracy compared to previous versions and other contemporary detectors.
YOLOv10 has been extensively tested on standard benchmarks like COCO, demonstrating superior performance and efficiency. The model achieves state-of-the-art results across different variants, showcasing significant improvements in latency and accuracy compared to previous versions and other contemporary detectors.
## Comparisons
Compared to other state-of-the-art detectors:
- YOLOv10-S / X are 1.8× / 1.3× faster than RT-DETR-R18 / R101 with similar accuracy
- YOLOv10-B has 25% fewer parameters and 46% lower latency than YOLOv9-C at same accuracy
- YOLOv10-L / X outperform YOLOv8-L / X by 0.3 AP / 0.5 AP with 1.8× / 2.3× fewer parameters
Here is a detailed comparison of YOLOv10 variants with other state-of-the-art models:
The Ultralytics team is actively working on officially integrating the YOLOv10 models into the `ultralytics` package. Once the integration is complete, the usage examples shown below will be fully functional. Please stay tuned by following our social media and [GitHub repository](https://github.com/ultralytics/ultralytics) for the latest updates on YOLOv10 integration. We appreciate your patience and excitement! 🚀
YOLOv10 sets a new standard in real-time object detection by addressing the shortcomings of previous YOLO versions and incorporating innovative design strategies. Its ability to deliver high accuracy with low computational cost makes it an ideal choice for a wide range of real-world applications.
YOLOv10 sets a new standard in real-time object detection by addressing the shortcomings of previous YOLO versions and incorporating innovative design strategies. Its ability to deliver high accuracy with low computational cost makes it an ideal choice for a wide range of real-world applications.
## Citations and Acknowledgements
## Citations and Acknowledgements
We would like to acknowledge the YOLOv10 authors for their extensive research to build upon the Ultralytics framework:
We would like to acknowledge the YOLOv10 authors from [Tsinghua University](https://www.tsinghua.edu.cn/en/) for their extensive research and significant contributions to the [Ultralytics](https://ultralytics.com) framework:
!!! Quote ""
!!! Quote ""
@ -80,8 +169,9 @@ We would like to acknowledge the YOLOv10 authors for their extensive research to
author={Ao Wang, Hui Chen, Lihao Liu, et al.},
author={Ao Wang, Hui Chen, Lihao Liu, et al.},
journal={arXiv preprint arXiv:2405.14458},
journal={arXiv preprint arXiv:2405.14458},
year={2024},
year={2024},
institution={Tsinghua University},
license = {AGPL-3.0}
license = {AGPL-3.0}
}
}
```
```
For detailed implementation and experimental results, please refer to the YOLOv10 [research paper](https://arxiv.org/pdf/2405.14458).
For detailed implementation, architectural innovations, and experimental results, please refer to the YOLOv10 [research paper](https://arxiv.org/pdf/2405.14458) and [GitHub repository](https://github.com/THU-MIG/yolov10) by the Tsinghua University team.
Glenn Jocher
6 months ago
committed by
GitHub