Papers › Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.
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="1506.01497")
Code
Syntology Ran 59 of 124 code samples harvested from 33 repositories linked to this paper; 65 have no recorded run. Of those that ran: 15 ran · honoured contract; 5 ran · violated contract; 16 ran · our draft was wrong; 12 ran · fixture could not drive it; 11 ran with no contract checked.
By repository: community (archive-listed): 124 samples from 33 repositories, 59 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
196 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
124 samples harvested; 59 ran; 15 honoured the contract we drafted; 65 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: 42 of the 124 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 33 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.
f0c00a98a2d39aff · report
6c7ac8e6466bcea8 · report
c2609d337cc38d1f · report
f55438873775f578 · report
7bf221011b0422f3 · report
14ffa58eda68a7de · report
d3074fd4bb476f7c · report
07e2761ffff4d782 · report
2999eab920b83a84 · report
841a6839dbfe8def · report
a46037f2dfcbab55 · report
f5977f4c8117ba6b · report
060f8463b181bc2a · report
b23ecd8325e475af · report
e6f256cf0e6682f7 · report
bea564463ca31505 · report
c55a6b30f9bc962a · report
3d4054a97b39b3a3 · report
bd2b197f56d84807 · report
ed64f0c42ae635d5 · report
b3695ebe0c382b05 · report
b02278c1b3f3b63d · report
0902f7f6352e685e · report
591d88c9673c0fc7 · report
2ec9b42e568fb19f · report
0ca35377bdcd364d · report
b34cbddfcacf0cce · report
6c939ab027a6b144 · report
0101675a1b149608 · report
ad33fe7d19220e3a · report
0ae6f0a64b0b3de7 · report
9e8def059f5360f9 · report
93f6fc328f31783a · report
23846102391f5532 · report
53cfb74c9acaebd7 · report
1e455c239bf7bdd6 · report
13739dd398ad8d69 · report
92b2156d0a7c6228 · report
08a5a1f47d119996 · report
85b003e6c83cb43b · report
ed39bf5fccc27256 · report
72307683ca04669e · report
fc1b18c3f9aaa651 · report
341516a8780d42ca · report
f7906400dae5e223 · report
9b8ca176346f3308 · report
048178ed2b542c16 · report
d3ee28edbd99f270 · report
797ff1b51915a853 · report
5502a789c2da0e5e · report
1e7714622ee1d965 · report
7559856164716a11 · report
0bcc7a97c7be815f · report
b2b63219c5d0e840 · report
49a5d8f734b321e2 · report
9d838d87e099d632 · report
a9edc972dffb9ce0 · report
b7d2d0749e1e9570 · report
95c31c78be42f723 · report
7b4b3a8f4fa9ec15 · report
d1c3c2852d099c73 · report
3b0bdd925eedfe2c · report
4cb24822483c1752 · report
fb987e73a2964a12 · report
8eef7ca47d47b9f1 · report
b9b9aab92d838a60 · report
ee229462d5538d85 · report
316fb42e9e6ed79e · report
938e375f128a8df4 · report
74fe489012952707 · report
ac90f7d3335fdbab · report
fa670f0881785f6e · report
9a30ff0e4c1b655e · report
d58371c318e7709f · report
fed3cf60d5b8bbc7 · report
55548a13fbb28f9d · report
48b4b7f4e22caf1d · report
84dcf978d5570762 · report
f582f4ac06db0801 · report
9a18f93db09b6ce9 · report
74bebe7a4353815b · report
d24c99284beca7a6 · report
33a0229e07c8747c · report
abb22cc6e4d9dd2a · report
fdbedfdf345b25aa · report
dca9a52de31f7da0 · report
b77ffbba2e1a9d86 · report
d4f2ade15edff997 · report
ffec5c8e487649a5 · report
4cbc23322099c4d4 · report
3be9228820b46ef3 · report
9f3cea1708a8a9db · report
2472016d914a87af · report
4786edbc775d299d · report
d824616e9b9ddc19 · report
7aa69848bcaff4ce · report
d6a99ec714147ac1 · report
f6201297533ad4f1 · report
9cf5bfef281ed505 · report
bbefc23ca8ceb023 · report
f1c71fc2ea63fd48 · report
5b5529d8420c48f4 · report
0eafc51289a49033 · report
8b2bf0b430e58bfd · report
c47028fc993839d4 · report
e9c0ddb56a18032c · report
2c0abbbca0945496 · report
5fa7938265b57599 · report
9ca0a7e84323075d · report
6f2e5eabaa000438 · report
30a399b69da9471f · report
ce1478c996b4df2f · report
ba1ccbc77a38e09f · report
1d64dd6265848b12 · report
f3eb19077165d8d2 · report
81dd949ea3cb5b13 · report
8178d0257544aab2 · report
48409da9351f9c1e · report
8a015c012f507631 · report
ec3e5aa793d6ce69 · report
6a03223a863a8a3d · report
3ae40f3a627d9d39 · report
d3e019b11b709edb · report
a832e5017f504280 · report
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 2D Object Detection | SARDet-100K | F-RCNN | box mAP | 49.0 | #9 of 13 | Archive leaderboard | report |
| Object Counting | CARPK | Faster R-CNN (2015) | MAE | 39.88 | #13 of 15 | Archive leaderboard | report |
| Object Counting | CARPK | Faster R-CNN (2015) | RMSE | 47.67 | #13 of 15 | Archive leaderboard | report |
| Object Detection | COCO-O | Faster R-CNN (ResNet-50-FPN) | Average mAP | 16.4 | #40 of 45 | Archive leaderboard | report |
| Object Detection | COCO-O | Faster R-CNN (ResNet-50-FPN) | Effective Robustness | -0.41 | #40 of 45 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 (15+5) | Faster R-CNN | MAP | 73.2% | #1 of 1 | Archive leaderboard | report |
| Object Detection | PKU-DDD17-Car | Faster-RCNN | mAP50 | 80.2 | #1 of 1 | Archive leaderboard | report |
| Object Detection | UA-DETRAC | Faster R-CNN | mAP | 58.45 | #7 of 9 | Archive leaderboard | report |
| Real-Time Object Detection | PASCAL VOC 2007 (15+5) | Faster R-CNN | FPS | 7.0 | #1 of 1 | Archive leaderboard | report |
| Real-Time Object Detection | PASCAL VOC 2007 (15+5) | Faster R-CNN | MAP | 73.2 | #1 of 1 | Archive leaderboard | report |
| Robust Object Detection | Cityscapes | Baseline | mPC [AP] | 15.4 | #13 of 13 | Archive leaderboard | report |
| Vessel Detection | Vessel detection Dateset | Faster RCNN | AP | 64.3% | #2 of 3 | 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: Faster R-CNN, RPN
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