DAMO-YOLO : A Report on Real-Time Object Detection Design

By Xianzhe Xu, Yiqi Jiang, Weihua Chen, Yi-Li Huang, Yuan Zhang, Xiuyu Sun. arXiv.org, 2022

355 citations recorded by the source corpus.

In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series. DAMO-YOLO is extended from YOLO with some new technologies, including Neural Architecture Search (NAS), efficient Reparameterized Generalized-FPN (RepGFPN), a lightweight head with AlignedOTA label assignment, and distillation enhancement. In particular, we use MAE-NAS, a method guided by the principle of maximum entropy, to search our detection backbone under the constraints of low latency and high performance, producing ResNet/CSP-like structures with spatial pyramid pooling and focus modules. In the design of necks and heads, we follow the rule of ``large neck, small head''.We import Generalized-FPN with accelerated queen-fusion to build the detector neck and upgrade its CSPNet with efficient layer aggregation networks (ELAN) and reparameterization. Then we investigate how detector head size affects detection performance and find that a heavy neck with only one task projection layer would yield better results.In addition, AlignedOTA is proposed to solve the misalignment problem in label assignment. And a distillation schema is introduced to improve performance to a higher level. Based on these new techs, we build a suite of models at various scales to meet the needs of different scenarios. For general industry requirements, we propose DAMO-YOLO-T/S/M/L. They can achieve 43.6/47.7/50.2/51.9 mAPs on COCO with the latency of 2.78/3.83/5.62/7.95 ms on T4 GPUs respectively. Additionally, for edge devices with limited computing power, we have also proposed DAMO-YOLO-Ns/Nm/Nl lightweight models. They can achieve 32.3/38.2/40.5 mAPs on COCO with the latency of 4.08/5.05/6.69 ms on X86-CPU. Our proposed general and lightweight models have outperformed other YOLO series models in their respective application scenarios.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7ac3c60fad951107dfaec985d2160937538d6818

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

Citations in the corpus

YOLOv10: Real-Time End-to-End Object Detection (2024, background): “Furthermore, the model architecture design remains a fundamental challenge for YOLOs, which exhibits an important impact on the accuracy and speed [50, 17, 71, 8].”
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS (2023, methodology): “15 DAMO-YOLO DAMO-YOLO [110] was published in ArXiv in November 2022 by Alibaba Group.”
Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation (2024, neutral): “The YOLO series methods [1], [2], [3], [4], [5], [7], [8], [22], [47], [48], [49], [50], [51] are typically composed of two main components: backbone and neck.”
YOLOv12: Attention-Centric Real-Time Object Detectors (2025, neutral): “We report more details of the results in Table 6”
Effective Whole-body Pose Estimation with Two-stages Distillation (2023, methodology): “This technique enables a student to inherit knowledge from a larger teacher and has found widespread application in various tasks, such as classification [69], detection [49], and segmentation [28].”
A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond (2023, methodology): “DAMO-YOLO [97] was published in ArXiv in November 2022 by Alibaba Group.”
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.”