Papers › YOLO9000: Better, Faster, Stronger
YOLO9000: Better, Faster, Stronger
Joseph Redmon, Ali Farhadi
We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster RCNN with ResNet and SSD while still running significantly faster. Finally we propose a method to jointly train on object detection and classification. Using this method we train YOLO9000 simultaneously on the COCO detection dataset and the ImageNet classification dataset. Our joint training allows YOLO9000 to predict detections for object classes that don't have labelled detection data. We validate our approach on the ImageNet detection task. YOLO9000 gets 19.7 mAP on the ImageNet detection validation set despite only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. But YOLO can detect more than just 200 classes; it predicts detections for more than 9000 different object categories. And it still runs in real-time.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="1612.08242")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1612.08242", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1612.08242")
Code
Syntology 60 code samples harvested from 17 repositories linked to this paper: 44 ran (of which 0 constructed an object rather than computing a result; 33 with no instrument failure: 1 honoured, 4 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 16 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 60 samples from 17 repositories, 44 ran (33 with no instrument failure; 11 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 16 of its repositories that Syntology harvested for other papers:
- 3epochs/you-only-look-once, community (archive-listed): harvested for another paper, listed under the repository
- RobbertBrand/Yolo-Tensorflow-Implementation, community (archive-listed): harvested for another paper, listed under the repository
- Vijayabhaskar96/Object-Detection-Algorithms, community (archive-listed): harvested for another paper, listed under the repository
- alia21/VechicleDetection-and-Traccking, community (archive-listed): harvested for another paper, listed under the repository
- glouppe/info8010-deep-learning, community (archive-listed): harvested for another paper, listed under the repository
- km1414/CNN-models, community (archive-listed): harvested for 3 other papers, listed under the repository
- leon-liangwu/MaskYolo_Caffe, community (archive-listed): harvested for another paper, listed under the repository
- michhar/azureml-keras-yolov3-custom, community (archive-listed): harvested for another paper, listed under the repository
- s1r2ikanth/Atunomous-Driving-Application--For-Car-detection, community (archive-listed): harvested for another paper, listed under the repository
- samson6460/tf2_YOLO, community (archive-listed): harvested for 2 other papers, listed under the repository
- tanjeffreyz/yolo-v1, community (archive-listed): harvested for another paper, listed under the repository
- thtrieu/darkflow, community (archive-listed): harvested for another paper, listed under the repository
- usnistgov/object-detection-yolov3, community (archive-listed): harvested for another paper, listed under the repository
- westerndigitalcorporation/YOLOv3-in-PyTorch, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleDetection, community (archive-listed): harvested for another paper, listed under the repository
- eavise-kul/lightnet, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
231 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
60 samples harvested: 44 ran (of which 0 constructed an object rather than computing a result; 33 with no instrument failure: 1 honoured, 4 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 16 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 23 of the 60 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 17 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
2e0088f9f6c77ccd · report
fixture: signature cx:float/0/float, cy:float/0/float, w:float/0/float, h:float/0/float · returned tuple · level recorded 2026-09-22 ba28b6ff72c46019 · report
fixture: signature xmin:float/0/float, ymin:float/0/float, xmax:float/0/float, ymax:float/0/float · returned tuple · level recorded 2026-09-22 884ec4546c029f7f · report
fixture: signature parsed_args:Namespace/0/? · returned Namespace · level recorded 2026-09-22 b29442449c79d09a · report
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket LAYERS/yolov3_model.py unverified no licence file found · pointer only ·
43717c1b14b4a9b0 · report
08b35ceb5c98627b · report
fixture: signature self:DummySelf/0/?, b:BoundingBox/0/?, h:int/0/int, w:int/0/int, threshold:float/0/float · returned tuple · level recorded 2026-09-22 5f574b0cfa25fc89 · report
a9298b59a1355a85 · report
fixture: signature class_names:list/1/str · returned list · level recorded 2026-09-26 census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket CODE.py ran MIT (permissive) ·
28063e4bcb75b1c9 · report
fixture: signature box1:tuple/1/int, box2:tuple/1/int · returned float · level recorded 2026-09-26 cb646fad1038456f · report
fixture: signature classes_path:str/0/str · returned list · level recorded 2026-09-26 57230ba78de7b9b8 · report
3b40b5666c482d42 · report
fixture: signature config_file:str/0/str · returned StringIO · level recorded 2026-09-22 4f1f7cada8b66cdf · report
fixture: signature top1:int/0/int, left1:int/0/int, bottom1:int/0/int, right1:int/0/int, top2:int/0/int, left2:int/0/int, bottom2:int/0/int, right2:int/0/int · returned int · level recorded 2026-09-26 c788753700b39fa0 · report
fixture: signature top1:int/0/int, left1:int/0/int, bottom1:int/0/int, right1:int/0/int, top2:int/0/int, left2:int/0/int, bottom2:int/0/int, right2:int/0/int · returned float · level recorded 2026-09-26 cf34a278d5d3be18 · report
fixture: signature image:Image/0/? · returned ndarray · level recorded 2026-09-24 90d8d1632f180839 · report
fixture: signature detections_from_previous_crop:DataFrame/0/?, all_image_detections:DataFrame/0/? · returned DataFrame · level recorded 2026-09-26 22f3a2e69db46101 · report
11cf37349343b417 · report
ff92ad8f00e93bbc · report
fixture: signature x:tuple/1/int, centroids:list/1/tuple · returned ndarray · level recorded 2026-09-22 1a3fa3dda9a8b100 · report
fixture: signature X:ndarray/2/float, centroids:list/1/tuple · returned float64 · level recorded 2026-09-22 78d482d2a7373f3c · report
fixture: signature ctype:callable/0/?, values:list/1/int · returned c_int_Array_5 · level recorded 2026-09-22 census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket darknet.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted licence not identified · pointer only ·
9bca95aee23d1241 · report
fixture: signature probs:list/1/float · returned int · level recorded 2026-09-22 b78a5e60fc79a562 · report
612173776554210f · report
fixture: signature xy:ndarray/4/float, wh:ndarray/4/float, ratio:ndarray/1/float, grid_size:tuple/1/int, rescaled_anchors:ndarray/2/float · returned ndarray · level recorded 2026-09-22 5e786628b4af4cda · report
fixture: signature wh:ndarray/2/float, ratio:ndarray/1/float, rescaled_anchors:ndarray/2/float · returned ndarray · level recorded 2026-09-22 35834cd7597a3334 · report
fixture: signature xy:ndarray/4/float, ratio:ndarray/1/int, grid_size:tuple/1/int · returned ndarray · level recorded 2026-09-22 94cad4bc0776217e · report
fixture: signature in_num:int/0/int, out_num:int/0/int, kernel_size:int/0/int, padding:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22 f6caf2197aa6a134 · report
fixture: signature num_classes:int/0/int · returned Darknet53 · level recorded 2026-09-22 8af48f9afc13d286 · report
fixture: signature videocontext:VideoContext/0/?, position:int/0/int · returned int · level recorded 2026-09-26 0c2d05f1318b18ad · report
fixture: signature videocontext:VideoContext/0/?, framenum:int/0/int · returned int · level recorded 2026-09-26 b287113ad972c375 · report
fixture: signature img:ndarray/2/int, orient:str/0/str, thresh_min:int/0/int, thresh_max:int/0/int · returned ndarray · level recorded 2026-09-26 06697fe6a2ba0179 · report
fixture: signature img:ndarray/3/int, nbins:int/0/int, bins_range:tuple/1/int · returned ndarray · level recorded 2026-09-26 99bd6d7b66f50ce9 · report
fixture: signature img:ndarray/3/int, color_space:str/0/str · returned ndarray · level recorded 2026-09-26 43d4618faca2c22c · report
fixture: signature img:ndarray/2/float, orient:int/0/int, pix_per_cell:int/0/int, cell_per_block:int/0/int, vis:bool/0/bool, feature_vec:bool/0/bool · returned ndarray · level recorded 2026-09-26 676f025f792cabd0 · report
fixture: signature img:ndarray/3/int, nx:int/0/int, ny:int/0/int · returned tuple · level recorded 2026-09-26 1f815127810a2689 · report
fixture: signature anchors_path:str/0/str · returned ndarray · level recorded 2026-09-26 030256402fcc0051 · report
fixture: signature anchors_path:str/0/str · returned ndarray · level recorded 2026-09-26 982f4a7d0e696253 · report
fixture: signature input_shape:tuple/1/int · returned tuple · level recorded 2026-09-26 a453313c9bf6d515 · report
8d685c46e94a7804 · report
fixture: signature x:EagerTensor/4/float, n_filters:int/0/int, f:tuple/1/int, padding:str/0/str, activation:str/0/str · returned EagerTensor · level recorded 2026-09-26 a094a1272071effc · report
fixture: signature builder:MockBuilder/0/?, inputs:list/1/MockInput, batch_sizes:list/1/int · returned list · level recorded 2026-09-26 43d2dd422fda72e4 · report
fixture: signature gt:list/1/int, pr:list/1/int · returned tuple · level recorded 2026-09-26 d556ce65e916bfce · report
fixture: signature capture_width:int/0/int, capture_height:int/0/int, display_width:int/0/int, display_height:int/0/int, framerate:int/0/int · returned str · level recorded 2026-09-26 census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket metrics.py ran fingerprinted MIT (permissive) ·
a284e3322157b771 · report
fixture: signature box1:list/1/int, box2:list/1/int · returned float · level recorded 2026-09-26 census: 7 implementations from 6 papers, 7 distinct outputs across 2 buckets, one shared input per bucket yolo_train.py ran MIT (permissive) ·
a1ceaadc2f636a2a · report
fixture: signature y_true:EagerTensor/4/float, y_pred:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-26 66e945e5f773b5dd · report
ed23764e4d82f481 · report
fixture: signature input_shape:tuple/1/int · returned tuple · level recorded 2026-09-22 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 5 of 11, arg 1: rank 3, kind float, dtype float32 tiny-yolo2-reduced.py ran · violated contract fingerprinted no licence file found · pointer only ·
d989af7b3606773e · report
fixture: signature image:Tensor/3/float · returned Tensor · level recorded 2026-09-22 census: 36 implementations from 56 papers, 7 distinct outputs across 3 buckets, one shared input per bucket yolo_utils.py ran fingerprinted MIT (permissive) ·
061232c6642c251d · report
fixture: signature arr:ndarray/2/float · returned ndarray · level recorded 2026-09-26 94187d0efaafc336 · report
fixture: signature t:int/0/int, l:int/0/int, b:int/0/int, r:int/0/int · returned list · level recorded 2026-09-26 b5e422e275737fd0 · report
fixture: signature x:int/0/int, y:int/0/int, w:int/0/int, h:int/0/int · returned list · level recorded 2026-09-26 8e637615e3f0d99e · report
fixture: signature y_true:EagerTensor/4/float, y_pred:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-26 0c0a819ce651007b · report
fixture: signature img:ndarray/3/int, dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-26 Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Counting | CARPK | YOLO9000opt (2017) | MAE | 130.40 | #14 of 15 | Archive leaderboard | report |
| Object Counting | CARPK | YOLO9000opt (2017) | RMSE | 172.46 | #14 of 15 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 | YOLO v2 | MAP | 78.6% | #15 of 30 | Archive leaderboard | report |
| Object Detection | UA-DETRAC | YOLOv2 | mAP | 57.72 | #8 of 9 | 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: Fast-YOLOv2, YOLOv2
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