Papers › Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation

11 Nov 2013CVPR 2014 6arXiv:1311.2524archive 2025-07-28

Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

PaperPDFConference PDFCodeCode 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="1311.2524")

Code

Syntology Ran 1 of 17 code samples harvested from 5 repositories linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: community (archive-listed): 17 samples from 5 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.

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

Anmol6/capshun mentioned on GitHub report
Coldmooon/RCNN-for-Latest-Caffe mentioned on GitHubBSD-2-Clause report
Halesu/4th-ML100Days mentioned on GitHubtf report
eyangch/caloreasyv2 mentioned on GitHubtfMIT report
jameswang287/Car-Detection mentioned on GitHubpytorch report
jiangbestone/DetectRCNN mentioned on GitHubpytorch report
jiangbestone/DetectRccn mentioned on GitHubpytorchMIT report
jiangbestone/detect_rcnn mentioned on GitHubpytorch report
jtiger958/pytorch-computer-vision-basic mentioned on GitHubpytorch report
quocdat32461997/Mask_RCNN mentioned on GitHubtf report
rbgirshick/rcnn mentioned on GitHubBSD-2-Clause report
s1ns11/FasterR-CNN mentioned on GitHubpytorch report
sbetageri/MaskRCNN mentioned on GitHubpytorchMIT report
soumik12345/RCNN mentioned on GitHubtf report
zjZSTU/R-CNN mentioned on GitHubpytorchApache-2.0 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

17 samples harvested; 1 ran; 1 honoured the contract we drafted; 16 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.

1ran · honoured contract
16unverified

Licence: 0 of the 17 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 5 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.

autopad jiangbestone/DetectRccn/models/common.py community (archive-listed) ran · honoured contract MIT (permissive) · 988a3c854b1b13d0 · report
BasicBlock jiangbestone/DetectRCNN/models/rcnn.py community (archive-listed) unverified MIT (permissive) · b298ad3f62f43096 · report
Srch eyangch/caloreasyv2/other/genObj.py community (archive-listed) unverified MIT (permissive) · 619f23a2d62046fc · report
detObj eyangch/caloreasyv2/other/predObj.py community (archive-listed) unverified MIT (permissive) · 39abe3f65f9e62d4 · report
detect1Image jiangbestone/DetectRccn/trainval_net.py community (archive-listed) unverified MIT (permissive) · 9591aa591e61cafc · report
floodFill eyangch/caloreasyv2/other/genObj.py community (archive-listed) unverified MIT (permissive) · de12b7de85b85f89 · report
gdrive_download jiangbestone/DetectRccn/lib/google_utils.py community (archive-listed) unverified MIT (permissive) · aa2a7d97e3d5fc20 · report
getDiff eyangch/caloreasyv2/other/genObj.py community (archive-listed) unverified MIT (permissive) · 734d0a8683d1995c · report
get_hard_negatives zjZSTU/R-CNN/py/linear_svm.py community (archive-listed) unverified Apache-2.0 (permissive) · cea1619962cf4c2f · report
get_model zjZSTU/R-CNN/py/bbox_regression.py community (archive-listed) unverified Apache-2.0 (permissive) · 8ae1a283374838b2 · report
get_model zjZSTU/R-CNN/py/car_detector.py community (archive-listed) unverified Apache-2.0 (permissive) · e334f0be9e7625bc · report
get_rects zjZSTU/R-CNN/py/selectivesearch.py community (archive-listed) unverified Apache-2.0 (permissive) · e01cf73f59c39e03 · report
hinge_loss zjZSTU/R-CNN/py/linear_svm.py community (archive-listed) unverified Apache-2.0 (permissive) · 71a4ab2e9cafc6f4 · report
iou zjZSTU/R-CNN/py/utils/util.py community (archive-listed) unverified Apache-2.0 (permissive) · c3d6dab5e0f17548 · report
parse_car_csv zjZSTU/R-CNN/py/utils/util.py community (archive-listed) unverified Apache-2.0 (permissive) · 1b4a7132cc8b77de · report
predictions jiangbestone/detect_rcnn/trainval_net.py community (archive-listed) unverified MIT (permissive) · 759a05b23a9dc5e3 · report
train_model zjZSTU/R-CNN/py/finetune.py community (archive-listed) unverified Apache-2.0 (permissive) · b5b24a630b2d8c70 · report

Tasks

Object DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection PASCAL VOC 2007 R-CNN MAP 58.5% #26 of 30 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-CNN

ConvolutionMax PoolingR-CNNSVM

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