Papers › R-FCN: Object Detection via Region-based Fully Convolutional Networks

R-FCN: Object Detection via Region-based Fully Convolutional Networks

20 May 2016NeurIPS 2016 12arXiv:1605.06409archive 2025-07-28

Jifeng Dai, Yi Li, Kaiming He, Jian Sun

We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image. To achieve this goal, we propose position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection. Our method can thus naturally adopt fully convolutional image classifier backbones, such as the latest Residual Networks (ResNets), for object detection. We show competitive results on the PASCAL VOC datasets (e.g., 83.6% mAP on the 2007 set) with the 101-layer ResNet. Meanwhile, our result is achieved at a test-time speed of 170ms per image, 2.5-20x faster than the Faster R-CNN counterpart. Code is made publicly available at: https://github.com/daijifeng001/r-fcn

PaperPDFConference PDFCodeCode 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="1605.06409")

Code

Syntology Ran 1 of 11 code samples harvested from 3 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 11 samples from 3 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

daijifeng001/r-fcn officialmentioned in papermentioned on GitHubmxnetNOASSERTION report
Code-0x00/caffe_windows mentioned on GitHub report
Feynman27/pytorch-detect-rfcn mentioned on GitHubpytorchMIT report
MIhappen/CaffeSourceCode mentioned on GitHubNOASSERTION report
MonsterPeng/Deformable-ConvNets-master mentioned on GitHubtfApache-2.0 report
Qengineering/Rfcn_ncnn mentioned on GitHubBSD-3-Clause report
TangDL/DCN mentioned on GitHubtfMIT report
TimVerion/caffe_rfcn mentioned on GitHubNOASSERTION report
chenbys/GuidedOffset mentioned on GitHubtf report
chenghuaiyu/caffe mentioned on GitHubNOASSERTION report
facebookresearch/detectron mentioned on GitHubpytorch report
fourmi1995/IronExperiment-DCN mentioned on GitHubmxnetMIT report
freeniliang/caffe-fastercnn-rfcn mentioned on GitHubNOASSERTION report
freeniliang/caffe-ssd mentioned on GitHubNOASSERTION report
ghamarian/rfcn mentioned on GitHubtf report
guanfuchen/Deformable-ConvNets mentioned on GitHubtfMIT report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2 report
macomino/TFM mentioned on GitHubtf report
makefile/frcnn mentioned on GitHub report
msracver/Deformable-ConvNets mentioned on GitHubmxnetMIT report
necla-ml/Deformable-ConvNets-py3 mentioned on GitHubmxnetMIT report
princewang1994/R-FCN.pytorch mentioned on GitHubpytorchMIT report
princewang1994/RFCN_CoupleNet.pytorch mentioned on GitHubpytorchMIT report
qilei123/DEEPLAB_4_RETINA mentioned on GitHubtfMIT report
qilei123/DEEPLAB_4_RETINAIMG mentioned on GitHubtfMIT report
qilei123/DeformableConvV2 mentioned on GitHubmxnetMIT report
qilei123/DeformableConvV2_crop mentioned on GitHubmxnetMIT report
qilei123/fpn_crop mentioned on GitHubmxnetMIT report
qilei123/fpn_crop_v1_5d mentioned on GitHubmxnetMIT report
qilei123/sod_v1 mentioned on GitHubmxnetMIT report
qilei123/sod_v1_demo mentioned on GitHubmxnetMIT report
stupidZZ/pyc_repo mentioned on GitHubmxnetMIT report
wincelinux/ai-dn-FasterRCNN-caffe mentioned on GitHubNOASSERTION report
xdever/RFCN-tensorflow mentioned on GitHubtf report
xiaoxu1025/r-fcn mentioned on GitHubtf report
xiaoyongzhu/Deformable-ConvNets mentioned on GitHubmxnetApache-2.0 report
zengzhaoyang/Weak_Detection mentioned on GitHubtfMIT report
zengzhaoyang/trident mentioned on GitHubmxnetMIT report
zzdxfei/defor_conv_mxnet_code mentioned on GitHubmxnetMIT 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

11 samples harvested; 1 ran; 0 honoured the contract we drafted; 10 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
10unverified

Licence: 0 of the 11 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.

conv3x3 princewang1994/RFCN_CoupleNet.pytorch/lib/model/couplenet/resnet_atrous.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_imdb Feynman27/pytorch-detect-rfcn/lib/datasets/factory.py community (archive-listed) unverified MIT (permissive) · 3be9228820b46ef3 · report
parse_rec princewang1994/R-FCN.pytorch/lib/datasets/voc_eval.py community (archive-listed) unverified MIT (permissive) · 0eafc51289a49033 · report
resnet18 princewang1994/RFCN_CoupleNet.pytorch/lib/model/couplenet/resnet_atrous.py community (archive-listed) unverified MIT (permissive) · 94ec2986ec97471a · report
resnet34 princewang1994/RFCN_CoupleNet.pytorch/lib/model/couplenet/resnet_atrous.py community (archive-listed) unverified MIT (permissive) · e937bd7ad7cf0909 · report
unique_boxes Feynman27/pytorch-detect-rfcn/lib/datasets/ds_utils.py community (archive-listed) unverified MIT (permissive) · 8a015c012f507631 · report
vg_eval princewang1994/R-FCN.pytorch/lib/datasets/vg_eval.py community (archive-listed) unverified MIT (permissive) · c485a145dcf5de8e · report
voc_ap princewang1994/R-FCN.pytorch/lib/datasets/voc_eval.py community (archive-listed) unverified MIT (permissive) · ec3e5aa793d6ce69 · report
voc_eval princewang1994/R-FCN.pytorch/lib/datasets/voc_eval.py community (archive-listed) unverified MIT (permissive) · 2f16ecec36118ba9 · report
xywh_to_xyxy Feynman27/pytorch-detect-rfcn/lib/datasets/ds_utils.py community (archive-listed) unverified MIT (permissive) · d3e019b11b709edb · report
xyxy_to_xywh Feynman27/pytorch-detect-rfcn/lib/datasets/ds_utils.py community (archive-listed) unverified MIT (permissive) · a832e5017f504280 · report

Tasks

ObjectObject DetectionReal-Time Object DetectionTranslationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection UA-DETRAC R-FCN mAP 69.87 #6 of 9 Archive leaderboard report
Real-Time Object Detection PASCAL VOC 2007 R-FCN FPS 9 #4 of 4 Archive leaderboard report
Real-Time Object Detection PASCAL VOC 2007 R-FCN MAP 80.5% #4 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: R-FCN

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingPosition-Sensitive RoI PoolingR-FCNReLUResidual BlockResidual ConnectionSPEED

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