Papers › RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

10 Jan 2019arXiv:1901.03353archive 2025-07-28

Cheng-Yang Fu, Mykhailo Shvets, Alexander C. Berg

Recently two-stage detectors have surged ahead of single-shot detectors in the accuracy-vs-speed trade-off. Nevertheless single-shot detectors are immensely popular in embedded vision applications. This paper brings single-shot detectors up to the same level as current two-stage techniques. We do this by improving training for the state-of-the-art single-shot detector, RetinaNet, in three ways: integrating instance mask prediction for the first time, making the loss function adaptive and more stable, and including additional hard examples in training. We call the resulting augmented network RetinaMask. The detection component of RetinaMask has the same computational cost as the original RetinaNet, but is more accurate. COCO test-dev results are up to 41.4 mAP for RetinaMask-101 vs 39.1mAP for RetinaNet-101, while the runtime is the same during evaluation. Adding Group Normalization increases the performance of RetinaMask-101 to 41.7 mAP. Code is at:https://github.com/chengyangfu/retinamask

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

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

chengyangfu/retinamask officialmentioned in paperpytorchSyntology: not harvested report
BIYTC/mobilenet_maskrcnn mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
FluteXu/ms-project mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
GuoLiuFang/maskrcnn-benchmark-lfs mentioned on GitHubpytorchMITSyntology: not harvested report
Iamal1/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Miracle1991/DetectionHub mentioned on GitHubpytorchSyntology: not harvested report
PeterTKovacs/zold137 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
SilvioGiancola/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
Zanderzt/TensorRT_Mask_RCNN mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Zhang-Jing-Xuan/MaskRCNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
Zhangyongtao123/maskrcnn_benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
ZhichengHuang/Food-Project mentioned on GitHubpytorchSyntology: not harvested report
abcxs/maskrcnn-contest mentioned on GitHubpytorchMITSyntology: not harvested report
adamvest/keypoint-baseline mentioned on GitHubpytorchSyntology: not harvested report
alannguyencs/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
banben/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
basaltzhang/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
bhfs9999/maskrcnn_isic mentioned on GitHubpytorchSyntology: not harvested report
bimal1988/detector mentioned on GitHubpytorchSyntology: not harvested report
ccchang1023/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
chencq1234/maskrcnn_facebook mentioned on GitHubpytorchMITSyntology: not harvested report
cshizhe/maskrcnn_benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
cyctrung/DPnet mentioned on GitHubpytorchMITSyntology: not harvested report
feng-lab/nuclei mentioned on GitHubpytorchMITSyntology: not harvested report
howardyclo/maskrcnn-benchmark mentioned on GitHubpytorchSyntology: not harvested report
huaifeng1993/JinNanCompetition2 mentioned on GitHubpytorchSyntology: not harvested report
iphyer/DefectDetection-MaskRCNN mentioned on GitHubpytorchSyntology: not harvested report
jahutwb/DL_dosimetry mentioned on GitHubpytorchMITSyntology: not harvested report
jonvthvn90/Project mentioned on GitHubpytorchMITSyntology: not harvested report
latentgnn/maskrcnn-benchmark-latentgnn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
lipengfeizju/Detection mentioned on GitHubpytorchMITSyntology: not harvested report
lippman1125/maskrcnn_benchmark_mobilenetv2 mentioned on GitHubpytorchMITSyntology: not harvested report
lssily/maskrcnn-benchmark-master mentioned on GitHubpytorchSyntology: not harvested report
lzrobots/dgmn mentioned on GitHubpytorchMITSyntology: not harvested report
markson14/WheatDet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
maxsenh/nuclei_cell_detect mentioned on GitHubpytorchSyntology: not harvested report
meryusha/seeds_faster mentioned on GitHubpytorchSyntology: not harvested report
monk-ai/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
mtcld/maskrcnn_benchmark_pytorch mentioned on GitHubpytorchSyntology: not harvested report
oulutan/Drone_FasterRCNN mentioned on GitHubpytorchMITSyntology: not harvested report
qilei123/maskrcnn_benchmark_ROP mentioned on GitHubpytorchSyntology: not harvested report
ryota2425/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
sadicLiu/mask_rcnn_code mentioned on GitHubpytorchSyntology: not harvested report
sarrrrry/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
squirrelim/sr-frcnn mentioned on GitHubpytorchSyntology: not harvested report
stigma0617/maskrcnn-benchmark-vovnet mentioned on GitHubpytorchMITSyntology: not harvested report
tuananh1007/Faster-R-CNN-and-Mask-R-CNN-in-PyTorch-1.0 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
vierachen/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
wangtuo0820/maskrcnn-benchmark-expansion mentioned on GitHubpytorchSyntology: not harvested report
worldlife123/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
wuyangzhang/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
zsl1996/mask mentioned on GitHubpytorchSyntology: not harvested report
zy0851/FB-m-RCNN mentioned on GitHubpytorchMITSyntology: 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival RetinaMask (ResNet-101-FPN) AP50 60.2 #168 of 220 Archive leaderboard report
Object Detection COCO minival RetinaMask (ResNet-101-FPN) AP75 44.1 #168 of 220 Archive leaderboard report
Object Detection COCO minival RetinaMask (ResNet-101-FPN) box AP 41.1 #168 of 220 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) AP50 62.5 #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) AP75 46.0 #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) APL 53.8 #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) APM 45.6 #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) APS 24.8 #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) Hardware Burden 12G #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNeXt-101-FPN-GN) box mAP 42.6 #172 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) AP50 58.6 #204 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) AP75 42.3 #204 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) APL 51.0 #204 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) APM 42.0 #204 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) APS 21.9 #204 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) Hardware Burden 9G #204 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaMask (ResNet-50-FPN) box mAP 39.4 #204 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: RetinaMask, Self-Adjusting Smooth L1 Loss

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNFocal LossGlobal Average PoolingGroup NormalizationGrouped ConvolutionKaiming InitializationMax PoolingNon Maximum SuppressionReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRetinaMaskRetinaNetRoIAlignSGD with MomentumSelf-Adjusting Smooth L1 LossStep DecayWeight 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