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

Code

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

chengyangfu/retinamask officialmentioned in paperpytorch report
BIYTC/mobilenet_maskrcnn mentioned on GitHubpytorchMIT report
FluteXu/ms-project mentioned on GitHubpytorch report
GuoLiuFang/maskrcnn-benchmark-lfs mentioned on GitHubpytorchMIT report
Iamal1/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
Miracle1991/DetectionHub mentioned on GitHubpytorch report
PeterTKovacs/zold137 mentioned on GitHubpytorchMIT report
SilvioGiancola/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
Zanderzt/TensorRT_Mask_RCNN mentioned on GitHubpytorchMIT report
Zhang-Jing-Xuan/MaskRCNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
Zhangyongtao123/maskrcnn_benchmark mentioned on GitHubpytorchMIT report
ZhichengHuang/Food-Project mentioned on GitHubpytorch report
abcxs/maskrcnn-contest mentioned on GitHubpytorchMIT report
adamvest/keypoint-baseline mentioned on GitHubpytorch report
alannguyencs/maskrcnn mentioned on GitHubpytorchMIT report
banben/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
basaltzhang/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
bhfs9999/maskrcnn_isic mentioned on GitHubpytorch report
bimal1988/detector mentioned on GitHubpytorch report
ccchang1023/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
chencq1234/maskrcnn_facebook mentioned on GitHubpytorchMIT report
cshizhe/maskrcnn_benchmark mentioned on GitHubpytorchMIT report
cyctrung/DPnet mentioned on GitHubpytorchMIT report
feng-lab/nuclei mentioned on GitHubpytorchMIT report
howardyclo/maskrcnn-benchmark mentioned on GitHubpytorch report
huaifeng1993/JinNanCompetition2 mentioned on GitHubpytorch report
iphyer/DefectDetection-MaskRCNN mentioned on GitHubpytorch report
jahutwb/DL_dosimetry mentioned on GitHubpytorchMIT report
jonvthvn90/Project mentioned on GitHubpytorchMIT report
latentgnn/maskrcnn-benchmark-latentgnn mentioned on GitHubpytorch report
lipengfeizju/Detection mentioned on GitHubpytorchMIT report
lippman1125/maskrcnn_benchmark_mobilenetv2 mentioned on GitHubpytorchMIT report
lssily/maskrcnn-benchmark-master mentioned on GitHubpytorch report
lzrobots/dgmn mentioned on GitHubpytorchMIT report
markson14/WheatDet mentioned on GitHubpytorchMIT report
maxsenh/nuclei_cell_detect mentioned on GitHubpytorch report
meryusha/seeds_faster mentioned on GitHubpytorch report
monk-ai/maskrcnn mentioned on GitHubpytorchMIT report
mtcld/maskrcnn_benchmark_pytorch mentioned on GitHubpytorch report
oulutan/Drone_FasterRCNN mentioned on GitHubpytorchMIT report
qilei123/maskrcnn_benchmark_ROP mentioned on GitHubpytorch report
ryota2425/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
sadicLiu/mask_rcnn_code mentioned on GitHubpytorch report
sarrrrry/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
squirrelim/sr-frcnn mentioned on GitHubpytorch report
stigma0617/maskrcnn-benchmark-vovnet mentioned on GitHubpytorchMIT report
vierachen/maskrcnn mentioned on GitHubpytorchMIT report
worldlife123/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
wuyangzhang/maskrcnn mentioned on GitHubpytorchMIT report
zsl1996/mask mentioned on GitHubpytorch report
zy0851/FB-m-RCNN mentioned on GitHubpytorchMIT 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

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