Papers › RTMDet: An Empirical Study of Designing Real-Time Object Detectors

RTMDet: An Empirical Study of Designing Real-Time Object Detectors

14 Dec 2022arXiv:2212.07784archive 2025-07-28

Chengqi Lyu, Wenwei Zhang, Haian Huang, Yue Zhou, Yudong Wang, Yanyi Liu, Shilong Zhang, Kai Chen

In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training techniques, the resulting object detector, named RTMDet, achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, outperforming the current mainstream industrial detectors. RTMDet achieves the best parameter-accuracy trade-off with tiny/small/medium/large/extra-large model sizes for various application scenarios, and obtains new state-of-the-art performance on real-time instance segmentation and rotated object detection. We hope the experimental results can provide new insights into designing versatile real-time object detectors for many object recognition tasks. Code and models are released at https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet.

PaperPDFCodeCode Syntology ran

In Syntology 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="2212.07784")

Code

Syntology Ran 3 of 20 code samples harvested from 3 repositories linked to this paper; 17 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: community (archive-listed): 20 samples from 3 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

14 repositories listed; official and paper-mentioned ones first.

open-mmlab/mmdetection officialpytorch report
HVision-NKU/Strip-R-CNN mentioned on GitHubpytorchNOASSERTION report
RangiLyu/mmdetection_test mentioned on GitHubpytorchApache-2.0 report
V3Det/mmdetection-V3Det mentioned on GitHubpytorchApache-2.0 report
cszzshi/SimD mentioned on GitHubpytorchApache-2.0 report
fiveai/MoCaE mentioned on GitHubpytorch report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmrotate mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmyolo mentioned on GitHubpytorchGPL-3.0 report
yuyi1005/point2rbox-mmrotate mentioned on GitHubpytorchApache-2.0 report
yxb-nku/strip-r-cnn mentioned on GitHubpytorchNOASSERTION 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

20 samples harvested; 3 ran; 0 honoured the contract we drafted; 17 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
17unverified

Licence: 0 of the 20 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

check_link RangiLyu/mmdetection_test/.dev_scripts/check_links.py community (archive-listed) ran Apache-2.0 (permissive) · 4e2dcdfe578946a0 · report
check_url RangiLyu/mmdetection_test/.dev_scripts/check_links.py community (archive-listed) ran Apache-2.0 (permissive) · cc93fdc812eca8f7 · report
process_model_info RangiLyu/mmdetection_test/.dev_scripts/convert_test_benchmark_script.py community (archive-listed) ran Apache-2.0 (permissive) · 3175ca3b1ec8c7b9 · report
bbox_flip open-mmlab/mmrotate/mmrotate/core/bbox/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · 376185dc39be213f · report
bbox_mapping_back open-mmlab/mmrotate/mmrotate/core/bbox/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · bc4459d2ed8a1d71 · report
check_path RangiLyu/mmdetection_test/.dev_scripts/check_links.py community (archive-listed) unverified Apache-2.0 (permissive) · fd08138d4bde9cfa · report
determine_gpus RangiLyu/mmdetection_test/.dev_scripts/convert_train_benchmark_script.py community (archive-listed) unverified Apache-2.0 (permissive) · fdef7359919a4918 · report
draw_rbboxes open-mmlab/mmrotate/mmrotate/core/visualization/image.py community (archive-listed) unverified Apache-2.0 (permissive) · 9432da2297676e37 · report
get_cls_results open-mmlab/mmrotate/mmrotate/core/evaluation/eval_map.py community (archive-listed) unverified Apache-2.0 (permissive) · d5e36bcdd9247df7 · report
get_multiscale_patch open-mmlab/mmrotate/mmrotate/core/patch/split.py community (archive-listed) unverified Apache-2.0 (permissive) · 01cb8ca0622cd942 · report
get_pattern_fill yuyi1005/point2rbox-mmrotate/mmrotate/models/task_modules/synthesis_generators/point2rbox_generator.py community (archive-listed) unverified Apache-2.0 (permissive) · ede6e43c8f430f7c · report
get_pattern_line yuyi1005/point2rbox-mmrotate/mmrotate/models/task_modules/synthesis_generators/point2rbox_generator.py community (archive-listed) unverified Apache-2.0 (permissive) · 45a05e5326bdf549 · report
get_pattern_rose yuyi1005/point2rbox-mmrotate/mmrotate/models/task_modules/synthesis_generators/point2rbox_generator.py community (archive-listed) unverified Apache-2.0 (permissive) · 1ed78f93e2bc1317 · report
map_masks open-mmlab/mmrotate/mmrotate/core/patch/merge_results.py community (archive-listed) unverified Apache-2.0 (permissive) · 101fcc7bda94ac46 · report
ordered_yaml_dump RangiLyu/mmdetection_test/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 8ff99a6bd2ebf598 · report
process_checkpoint RangiLyu/mmdetection_test/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 138e112e22b0314e · report
rbbox2result open-mmlab/mmrotate/mmrotate/core/bbox/transforms.py community (archive-listed) unverified Apache-2.0 (permissive) · ce792faad2a6fa37 · report
rotated_anchor_inside_flags open-mmlab/mmrotate/mmrotate/core/anchor/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 0ea25f06be11d42b · report
slide_window open-mmlab/mmrotate/mmrotate/core/patch/split.py community (archive-listed) unverified Apache-2.0 (permissive) · 4a5c249cf82b4cba · report
translate_bboxes open-mmlab/mmrotate/mmrotate/core/patch/merge_results.py community (archive-listed) unverified Apache-2.0 (permissive) · 743d0cc9f86f379e · report

Tasks

Instance SegmentationObjectObject DetectionObject Detection In Aerial ImagesObject RecognitionOne-stage Anchor-free Oriented Object DetectionOriented Object DetectionReal-Time Object DetectionReal-time Instance SegmentationSemantic Segmentationobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection In Aerial Images DOTA 1.0 RTMDet-R-l mAP 81.33% #1 of 2 Archive leaderboard report
Object Detection In Aerial Images DOTA 1.0 RTMDet-R-l (single scale) mAP 80.16% #2 of 2 Archive leaderboard report
Object Detection In Aerial Images HRSC2016 RTMDet-R-tiny mAP-07 90.6 #5 of 9 Archive leaderboard report
Object Detection In Aerial Images HRSC2016 RTMDet-R-tiny mAP-12 97.10 #5 of 9 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) RTMDet box AP 52.8 #38 of 82 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-x AP50 67.4 #1 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-x AP75 47.8 #1 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-x APL 65.5 #1 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-x APS 22.2 #1 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-x Frame (fps) 188 (RTX3090) #1 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-x mask AP 44.6 #1 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l AP50 66 #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l AP75 47.0 #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l APL 64.8 #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l APM 48.0 #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l APS 20.8 #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l Frame (fps) 271 (RTX3090) #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-l mask AP 43.7 #2 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m AP50 63.9 #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m AP75 45.1 #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m APL 63.1 #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m APM 46.4 #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m APS 19.3 #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m Frame (fps) 371 (RTX3090) #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-m mask AP 42.1 #3 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-s AP50 59.3 #22 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-s AP75 41.3 #22 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-s APL 60.3 #22 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-s APM 42.3 #22 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-s APS 15.1 #22 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO RTMDet-Ins-s Frame (fps) 518 (RTX3090) #22 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO-1k RTMDet-Ins-x APM 49.0 #1 of 1 Archive leaderboard report
Real-time Instance Segmentation multi30k_test_2017_mscoco RTMDet-Ins-s mask AP 38.7 #1 of 1 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

RTMDet

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