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

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

23 Nov 2022arXiv:2211.15444archive 2025-07-28

Xianzhe Xu, Yiqi Jiang, Weihua Chen, Yilun Huang, Yuan Zhang, Xiuyu Sun

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2211.15444")

Code

Syntology Ran 5 of 12 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alibaba/lightweight-neural-architecture-search officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
tinyvision/damo-yolo officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
modelscope/modelscope pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 5 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
4ran
7unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tinyvision/damo-yolo. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

channel_shuffle tinyvision/damo-yolo/damo/base_models/backbones/tinynas_mob.py official repository ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · b9da06d4f527dd6c · report
compute_on_dataset tinyvision/damo-yolo/damo/apis/detector_inference.py official repository ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 8d3929c7a8ced85c · report
get_latency tinyvision/damo-yolo/damo/utils/model_utils.py official repository ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 1e2aa107121385ed · report
get_norm tinyvision/damo-yolo/damo/base_models/core/ops.py official repository ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 03facae2ee7f6241 · report
make_divisible tinyvision/damo-yolo/damo/utils/model_utils.py official repository ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 890fb852f4b708f7 · report
batched_nms tinyvision/damo-yolo/damo/base_models/core/bbox_calculator.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · b5ec81c99b396e7a · report
depthwise_conv tinyvision/damo-yolo/damo/base_models/backbones/tinynas_mob.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · a3cf9b5f7f40034b · report
fast_nms tinyvision/damo-yolo/damo/base_models/core/bbox_calculator.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 6cce2ccd6ba1ab38 · report
get_activation tinyvision/damo-yolo/damo/base_models/core/ops.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · c95de3a17fdc99bc · report
load_tinynas_net tinyvision/damo-yolo/damo/base_models/backbones/tinynas_csp.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · de3143dabde8bd1f · report
load_tinynas_net tinyvision/damo-yolo/damo/base_models/backbones/tinynas_res.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · bdd5082e94f97421 · report
multiclass_nms tinyvision/damo-yolo/damo/base_models/core/bbox_calculator.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4b9a2b63bf7abc9e · report

Tasks

Neural Architecture SearchObject DetectionReal-Time Object Detectionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-L FPS (V100, b=1) 126 #53 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-L box AP 50.8 #53 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-M FPS (V100, b=1) 233 #59 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-M box AP 49.2 #59 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-S FPS (V100, b=1) 325 #68 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-S box AP 46 #68 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-T FPS (V100, b=1) 397 #73 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) DAMO-YOLO-T box AP 42 #73 of 82 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: DAMO-YOLO

DAMO-YOLOSpatial Pyramid Pooling

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections