Papers › Grid R-CNN

Grid R-CNN

29 Nov 2018CVPR 2019 6arXiv:1811.12030archive 2025-07-28

Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection. Different from the traditional regression based methods, the Grid R-CNN captures the spatial information explicitly and enjoys the position sensitive property of fully convolutional architecture. Instead of using only two independent points, we design a multi-point supervision formulation to encode more clues in order to reduce the impact of inaccurate prediction of specific points. To take the full advantage of the correlation of points in a grid, we propose a two-stage information fusion strategy to fuse feature maps of neighbor grid points. The grid guided localization approach is easy to be extended to different state-of-the-art detection frameworks. Grid R-CNN leads to high quality object localization, and experiments demonstrate that it achieves a 4.1% AP gain at IoU=0.8 and a 10.0% AP gain at IoU=0.9 on COCO benchmark compared to Faster R-CNN with Res50 backbone and FPN architecture.

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="1811.12030")

Code

Syntology Ran 0 of 3 code samples harvested from 1 repository linked to this paper; 3 have no recorded run.

By repository: community (archive-listed): 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

STVIR/Grid-R-CNN mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmdetection pytorchApache-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

3 samples harvested; 0 ran; 0 honoured the contract we drafted; 3 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.

3unverified

Licence: 0 of the 3 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 STVIR/Grid-R-CNN. “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.

grid_target STVIR/Grid-R-CNN/mmdet/core/mask/grid_target.py community (archive-listed) unverified Apache-2.0 (permissive) · a7c69b397e5d84e5 · report
random_jitter_single STVIR/Grid-R-CNN/mmdet/core/mask/grid_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 592d6a7af571845d · report
reduce_vision STVIR/Grid-R-CNN/mmdet/core/mask/grid_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 1bd410548921f582 · report

Tasks

2D Object DetectionNovel Object DetectionObjectObject DetectionObject Localizationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Object Detection SARDet-100K Grid RCNN box mAP 48.8 #10 of 13 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-101-FPN) AP50 60.3 #165 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-101-FPN) AP75 44.4 #165 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-101-FPN) APL 54.1 #165 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-101-FPN) APM 45.8 #165 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-101-FPN) APS 23.4 #165 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-101-FPN) box AP 41.3 #165 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-50-FPN) AP50 58.3 #187 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-50-FPN) AP75 42.4 #187 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-50-FPN) APL 51.5 #187 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-50-FPN) APM 43.8 #187 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-50-FPN) APS 22.6 #187 of 220 Archive leaderboard report
Object Detection COCO minival Grid R-CNN (ResNet-50-FPN) box AP 39.6 #187 of 220 Archive leaderboard report
Object Detection COCO test-dev Grid R-CNN (ResNeXt-101-FPN) AP50 63.0 #160 of 225 Archive leaderboard report
Object Detection COCO test-dev Grid R-CNN (ResNeXt-101-FPN) AP75 46.6 #160 of 225 Archive leaderboard report
Object Detection COCO test-dev Grid R-CNN (ResNeXt-101-FPN) APL 55.2 #160 of 225 Archive leaderboard report
Object Detection COCO test-dev Grid R-CNN (ResNeXt-101-FPN) APM 46.5 #160 of 225 Archive leaderboard report
Object Detection COCO test-dev Grid R-CNN (ResNeXt-101-FPN) APS 25.1 #160 of 225 Archive leaderboard report
Object Detection COCO test-dev Grid R-CNN (ResNeXt-101-FPN) box mAP 43.2 #160 of 225 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: Grid R-CNN

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDilated ConvolutionFCNFPNFaster R-CNNGlobal Average PoolingGrid R-CNNGrouped ConvolutionKaiming InitializationMax PoolingNon Maximum SuppressionRPNRandom Horizontal FlipReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIAlignRoIPoolSGD with MomentumSigmoid ActivationSoftmaxSyncBNWeight Decay

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