Papers › CenterMask : Real-Time Anchor-Free Instance Segmentation

CenterMask : Real-Time Anchor-Free Instance Segmentation

15 Nov 2019arXiv 2019 11arXiv:1911.06667archive 2025-07-28

Youngwan Lee, Jongyoul Park

We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector (FCOS) in the same vein with Mask R-CNN. Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise. We also present an improved backbone networks, VoVNetV2, with two effective strategies: (1) residual connection for alleviating the optimization problem of larger VoVNet and (2) effective Squeeze-Excitation (eSE) dealing with the channel information loss problem of original SE. With SAG-Mask and VoVNetV2, we deign CenterMask and CenterMask-Lite that are targeted to large and small models, respectively. Using the same ResNet-101-FPN backbone, CenterMask achieves 38.3%, surpassing all previous state-of-the-art methods while at a much faster speed. CenterMask-Lite also outperforms the state-of-the-art by large margins at over 35fps on Titan Xp. We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively. The Code is available at https://github.com/youngwanLEE/CenterMask.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 2 samples that ran has no recorded date.

youngwanLEE/CenterMask officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hades12580/centermask2 mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
mahdi-darvish/centermask mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
suvasis/birdnet2cs231n mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
youngwanLEE/centermask2 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
youngwanLEE/vovnet-detectron2 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhuoyang125/CenterMask2 mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran

Licence: 2 of the 2 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

youngwanLEE/CenterMask official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
str2bool in 533 papers demo/centermask_demo.py ran · violated contract no licence file found · pointer only · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
hades12580/centermask2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Max centermask/layers/wrappers.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 60b0f812f48bb79a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-25

Tasks

Instance SegmentationObject DetectionPanoptic SegmentationReal-Time Object DetectionReal-time Instance SegmentationSegmentationSemantic SegmentationSemi-Supervised Instance Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival CenterMask-VoVNetV2-99 (multi-scale) mask AP 42.5 #64 of 93 Archive leaderboard report
Instance Segmentation COCO minival CenterMask-VoVNetV2-99-3x mask AP 40.2 #76 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNet99 APL 54.3 #57 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNet99 APM 44.4 #57 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNet99 APS 24.4 #57 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNet99 mask AP 41.8 #57 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (single-scale) AP50 62.3 #68 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (single-scale) AP75 44.1 #68 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (single-scale) APL 57.0 #68 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (single-scale) APM 42.8 #68 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (single-scale) APS 20.1 #68 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (single-scale) mask AP 40.6 #68 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + X101-32x8d (single-scale) AP50 61.2 #77 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + X101-32x8d (single-scale) AP75 42.9 #77 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + X101-32x8d (single-scale) APS 19.7 #77 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + X101-32x8d (single-scale) mask AP 39.6 #77 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + ResNet-101-FPN mask AP 38.3 #86 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (multi-scale) AP50 66.2 #109 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (multi-scale) AP75 47.4 #109 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-99 (multi-scale) APS 27.2 #109 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-57 (single-scale) AP50 60.8 #110 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-57 (single-scale) APM 41.7 #110 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev CenterMask + VoVNetV2-57 (single-scale) APS 19.4 #110 of 112 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNet99 (multi-scale) AP50 67.8 #87 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNet99 (multi-scale) box AP 48.6 #87 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNetV2-99 (single-scale) APL 58.8 #113 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNetV2-99 (single-scale) APS 29.2 #113 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNetV2-99 (single-scale) box AP 45.6 #113 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (VoVNetV2-99, single-scale) APL 57.7 #121 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (VoVNetV2-99, single-scale) APS 28.5 #121 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (VoVNetV2-99, single-scale) box AP 44.9 #121 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNetV2-57 (single-scale) APM 48.3 #126 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNetV2-57 (single-scale) APS 27.7 #126 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+VoVNetV2-57 (single-scale) box AP 44.6 #126 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+X101-32x8d (single-scale) APL 57.1 #131 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+X101-32x8d (single-scale) APS 26.7 #131 of 220 Archive leaderboard report
Object Detection COCO minival CenterMask+X101-32x8d (single-scale) box AP 44.4 #131 of 220 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNetV2-99 (single-scale) AP50 64.5 #136 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNetV2-99 (single-scale) APL 57.6 #136 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNetV2-99 (single-scale) APM 48.3 #136 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNetV2-99 (single-scale) APS 27.8 #136 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNetV2-99 (single-scale) box mAP 45.8 #136 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNet2-57 (single-scale) AP50 63.1 #142 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNet2-57 (single-scale) AP75 48.6 #142 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNet2-57 (single-scale) APL 55.9 #142 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNet2-57 (single-scale) APS 27.1 #142 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask+VoVNet2-57 (single-scale) box mAP 44.7 #142 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask + X-101-32x8d (single-scale) AP50 63.4 #145 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask + X-101-32x8d (single-scale) AP75 48.4 #145 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask + X-101-32x8d (single-scale) APM 47.2 #145 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterMask + X-101-32x8d (single-scale) box mAP 44.6 #145 of 225 Archive leaderboard report
Real-time Instance Segmentation MSCOCO CenterMask-Lite (ResNet-50-FPN) APL 48.7 #16 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO CenterMask-Lite (ResNet-50-FPN) APM 34.7 #16 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO CenterMask-Lite (ResNet-50-FPN) APS 12.9 #16 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO CenterMask-Lite (ResNet-50-FPN) mask AP 32.9 #16 of 22 Archive leaderboard report
Semi-Supervised Instance Segmentation COCO 1% labeled data CenterMask2 (ResNet50) mask AP 10.07 #3 of 3 Archive leaderboard report
Semi-Supervised Instance Segmentation COCO 10% labeled data CenterMask2 (ResNet50) mask AP 22.08 #3 of 3 Archive leaderboard report
Semi-Supervised Instance Segmentation COCO 2% labeled data CenterMask2 (ResNet50) mask AP 13.46 #3 of 3 Archive leaderboard report
Semi-Supervised Instance Segmentation COCO 5% labeled data CenterMask2 (ResNet50) mask AP 18.04 #3 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: OSA (identity mapping + eSE), Spatial Attention-Guided Mask, VoVNetV2

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCenterMaskConcatenated Skip ConnectionConvolutionDense ConnectionsEffective Squeeze-and-Excitation BlockFCOSFPNGlobal Average PoolingGrouped ConvolutionKaiming InitializationMask R-CNNMax PoolingNon Maximum SuppressionOSA (identity mapping + eSE)One-Shot AggregationRPNReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIAlignSGD with MomentumSigmoid ActivationSoftmaxSpatial Attention-Guided MaskVoVNetVoVNetV2Weight 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