Papers › You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.
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="1506.02640")
Code
Syntology Ran 80 of 148 code samples harvested from 45 repositories linked to this paper; 68 have no recorded run. Of those that ran: 4 ran · honoured contract; 4 ran · violated contract; 12 ran · our draft was wrong; 17 ran · fixture could not drive it; 43 ran with no contract checked.
By repository: community (archive-listed): 141 samples from 45 repositories, 75 ran; 7 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
144 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.
Code Syntology ran Syntology
148 samples harvested; 80 ran; 4 honoured the contract we drafted; 68 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.
Licence: 98 of the 148 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 45 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.
12df2a4d4e2164d9 · report
9c798969164d0e3f · report
145089cb92dfe192 · report
6f5fcdaa1a66346b · report
925c307bbd79f4c9 · report
e51b597949497410 · report
6650a36a34670d48 · report
2a16f500c758e0fb · report
0a87cc68078b8130 · report
a2da5672bbc086d3 · report
2390515679b99339 · report
3ca60117f4fea257 · report
8d9039359a33a5fe · report
49d95f317c8411ea · report
161d0afc6942ee8a · report
d6893ebc8516e8db · report
95b9ab17a245bb24 · report
da55cf9866cb41e1 · report
c3b8937867a41dde · report
b445acdcf8d90d37 · report
32281a62359fa309 · report
2353b99f0ed68149 · report
0a3ef0b1d1f175b9 · report
d77878590fc2562c · report
28f729bdf2cd5201 · report
e2e6a6ad8e928647 · report
ffa921481b6a54c3 · report
f10b817692f95152 · report
8255067215f41bdd · report
d04bf9a09a736a52 · report
56cda48b112cd414 · report
1eb112cfe550ab4e · report
81ea9a33a5ab4d93 · report
320df1877e192cc4 · report
cd696cd247a1d09d · report
176e983db06d554b · report
04b987f5b68bd18e · report
4bd7300fab880607 · report
bb3b7889b05c820a · report
df07a80fb38aace5 · report
08b9a36f02f7601f · report
056c8fee6ae1bef5 · report
c40601ebebe70c7c · report
359c906d4db69e92 · report
14e1a3b5a738b277 · report
892cb24caebb0a10 · report
10cfbec4f3be1ace · report
1c48ff2f9d302176 · report
ddf34c500d70f342 · report
7e493fee89015615 · report
e604e68b98ad3d67 · report
f0af3d51eba51c84 · report
8cae105928c8d4d5 · report
1f8a9bd89881ff05 · report
b8f085d6c5d3158c · report
3ddd214dfdd86aa1 · report
bc3cd3f8c2d09fe5 · report
6f90433e21ba8f19 · report
f4499d26b7dc646c · report
f55bfd3ece60791a · report
74cfca8abd2312c1 · report
bcb84fefadf8f1fa · report
24b99483cb2ad9fe · report
0c95b3680456a44c · report
069755cdc2a2ef09 · report
18a29e8e5e9a500b · report
7365db21264af009 · report
f00fc53dade78ec7 · report
ae767f8e11bc29c3 · report
0fd1d4ddad6d4965 · report
8c476d2edc03b203 · report
475ce08eea0c1d56 · report
8825c7c596e27b6f · report
b67946e454ddeffe · report
1eda61cdae68b124 · report
2057b4a23e31413f · report
a45d154f27403998 · report
260a99ec862cd802 · report
fec58cc25dd3ba57 · report
c057bd9650bd0dc6 · report
eda64619e792c05a · report
3fe1851217b8ec35 · report
b46d1da4a9b2b0b8 · report
337cdd5af69139f2 · report
c2b31a3e1c24114b · report
d2a9890081a73f59 · report
c12303b151f3a90c · report
9aa35ba4f4e08349 · report
a00ae77a4a28dabe · report
7c51f318febec4c6 · report
c66677b9c6a0e77e · report
447eb6619a440649 · report
dbd50f0ac528eb9f · report
9e2bbdaa5c9223aa · report
bf6ddcf4a1ff539a · report
74958fb74c938445 · report
8580d2567c369d1b · report
35072159528d9ddc · report
c667e785054ac897 · report
97c9deb50f81deaa · report
b63e002a7056cc61 · report
84b11777c5a839c6 · report
b3d45ff221ab2fca · report
35670970a61cfa00 · report
d8b0a1eddc4b3a31 · report
97932725e48d9817 · report
da6cbf7c20be2c2f · report
6095748f22c356ca · report
80add88aecb7c89b · report
70163c108dc6e155 · report
088405cb6d3a795e · report
4d5a13b8cbf3b6ec · report
3043d27045351b58 · report
95f6f07be74f33f8 · report
34b4363943982e37 · report
695e57a8a1788336 · report
30d92a88a3be02e3 · report
753769e83a0400a8 · report
02f571daa3a824ed · report
9fc5ce38af667f86 · report
af3aa4a21f3c0e4c · report
568abf256295b483 · report
f30be690eeb808f8 · report
4b114c596ff86fb3 · report
57230ba78de7b9b8 · report
d41e171a51b58710 · report
6b9a303be4994ad6 · report
f5ebf80e23421885 · report
0c5521aa84ef774e · report
153cdf8151897fcd · report
32a661c28da22ab4 · report
3bb0e717dddf47f2 · report
36c9a9fa566464af · report
a30fc45c71b7e7ed · report
4c9fc5ac7434a6f0 · report
cf390a2d8ef760ae · report
ecefe9282a24dee5 · report
0c770552bf74476d · report
21f0bbe5ee20f22a · report
3461eb817fdce462 · report
72b45e92a4196a05 · report
612173776554210f · report
5e786628b4af4cda · report
35834cd7597a3334 · report
f35babe3912ec8b1 · report
ed23764e4d82f481 · report
5f574b0cfa25fc89 · report
43717c1b14b4a9b0 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Counting | CARPK | YOLO (2016) | MAE | 156.00 | #15 of 15 | Archive leaderboard | report |
| Object Counting | CARPK | YOLO (2016) | RMSE | 57.55 | #15 of 15 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 | YOLO | MAP | 63.4% | #24 of 30 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2012 | YOLO | MAP | 57.9 | #4 of 7 | Archive leaderboard | report |
| Real-Time Object Detection | PASCAL VOC 2007 | YOLO | FPS | 46.0 | #1 of 4 | Archive leaderboard | report |
| Real-Time Object Detection | PASCAL VOC 2007 | YOLO | MAP | 63.4% | #1 of 4 | 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: YOLOv1
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