Papers › Mask R-CNN

Mask R-CNN

20 Mar 2017ICCV 2017 10arXiv:1703.06870archive 2025-07-28

Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code has been made available at: https://github.com/facebookresearch/Detectron

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 140 code samples harvested from 30 repositories linked to this paper: 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified. Where Syntology's instrument failed: 17 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 139 samples from 29 repositories, 101 ran (77 with no instrument failure; 24 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.

No sample is linked to this paper from 16 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

facebookresearch/detectron mentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
2023-MindSpore-1/ms-code-207 mentioned on GitHubmindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-208 mentioned on GitHubmindsporeSyntology: not harvested report
AKASH2907/bird-species-classification mentioned on GitHubtfMITSyntology: 9 samples, 6 ran (2 instrument-failed) · 3 unverified report
AKASH2907/bird_species_classification mentioned on GitHubtfMITSyntology: not harvested report
Alexander-Whelan/Zeus mentioned on GitHubtfSyntology: not harvested report
Arthur-Shi/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
AshishSingh2261/Pedestrian_Instance_Segmentation mentioned on GitHubMITSyntology: not harvested report
Biantian/MscProject mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
BingkAI-B21CAP0161/C-Mask-Machine-Learning mentioned on GitHubtfSyntology: not harvested report
BlackAngel1111/Fast-RCNN mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
BupyeongHealer/Mask_RCNN_tf_2.x mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
CarstenIsert/DeepBurn mentioned on GitHubtfApache-2.0Syntology: not harvested report
ColdNoodler/py-faster-rcnn-cuda10 mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
DeNA/Chainer_Mask_R-CNN mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
DivJAth/DeepLearning5922 mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Residual Dense Network for Image Super-Resolution (arXiv:1802.08797; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
EmGarr/kerod mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Feature Pyramid Networks for Object Detection (arXiv:1612.03144; that paper's own run record: 33 ran (of which 9 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 5 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
ErikGDev/instance-segmentation mentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 9 ran (6 instrument-failed) · 2 unverified report
GAOwy123/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
GH3927/Mask-RCNN-applied-to-cranes mentioned on GitHubtfSyntology: not harvested report
George-Ogden/Mask-RCNN mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
KMnP/fashionpedia-api mentioned on GitHubtfSyntology: not harvested report
Krupal09/MaskRCNN-Demo mentioned on GitHubtfSyntology: not harvested report
Lopezurrutia/DSB_2018 mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
MIC-DKFZ/DetectionAndRegression mentioned on GitHubpytorchSyntology: not harvested report
MIC-DKFZ/RegRCNN mentioned on GitHubpytorchSyntology: not harvested report
Makunda/DeepLearningASL mentioned on GitHubSyntology: not harvested report
Mrnoorsingh/car-parking mentioned on GitHubSyntology: not harvested report
NVlabs/industreallib mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
NiravRaiyani/Mask-R-CNN-for-water-detection mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Qinhj07/ATOMCode mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
RaiyaniNirav/Mask-R-CNN-for-water-detection mentioned on GitHubtfSyntology: not harvested report
RajArPatra/Super-OCR mentioned on GitHubpytorchMITSyntology: not harvested report
Rakeshvd/Instance-Segmenation-of-MRI-scan-using-Mask-RCNN mentioned on GitHubtfSyntology: not harvested report
Rakeshvd/Semantic-Segmenation-of-MRI-scan-using-Mask-RCNN mentioned on GitHubtfSyntology: not harvested report
SUYEgit/Surgery-Robot-Detection-Segmentation mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
SfTI-Robotics/ROS-label-node mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
SonginCV/GMPHD_MAF mentioned on GitHubNOASSERTIONSyntology: not harvested report
SonginCV/GMPHD_SAF mentioned on GitHubNOASSERTIONSyntology: not harvested report
SonginCV/MAF_HDA mentioned on GitHubNOASSERTIONSyntology: not harvested report
StephenEkaputra/Mask_RCNN-TinyPascalVOC mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
TejasBajania/Mtech_pro mentioned on GitHubSyntology: not harvested report
TejasBajania/Mtech_thesis_project mentioned on GitHubSyntology: not harvested report
TuSimple/mx-maskrcnn mentioned on GitHubtfApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
UPCLJ/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
ZQPei/deep_sort_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple Online and Realtime Tracking with a Deep Association Metric (arXiv:1703.07402; that paper's own run record: 29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 4 honoured, 3 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
alexalm4190/Mask_RCNN-Vizzy_Hand mentioned on GitHubSyntology: not harvested report
alililia/ascend_maskrcnn_mobilenetv1 mentioned on GitHubmindsporeApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
alililia/gpu_maskrcnn_mobilenetv1 mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
asyrovprog/cs230project mentioned on GitHubNOASSERTIONSyntology: not harvested report
ayoolaolafenwa/PixelLib mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointRend: Image Segmentation as Rendering (arXiv:1912.08193; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
baodi23/hourglass-facekeypoints-detection mentioned on GitHubpytorchSyntology: not harvested report
beassssry/U mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
bethgelab/siamese-mask-rcnn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
boom85423/Cartoon-style-Stickers-Generator mentioned on GitHubpytorchSyntology: not harvested report
bowu1004/instance_segmentation_RealSense mentioned on GitHubpytorchSyntology: not harvested report
busyboxs/What-I-have-star mentioned on GitHubtfSyntology: not harvested report
busyboxs/faster_rcnn_voc mentioned on GitHubNOASSERTIONSyntology: not harvested report
casiopa/Madrid_Rooftops mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
charlesYangM/py-faster-rcnn-80.28 mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
charlesshang/fastmaskrcnn mentioned on GitHubtfApache-2.0Syntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
chenwuperth/ClaRAN mentioned on GitHubtfApache-2.0Syntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
chihyanghsu0805/object_detection_yolo mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to You Only Look Once: Unified, Real-Time Object Detection (arXiv:1506.02640; that paper's own run record: 89 ran (of which 27 constructed an object rather than computing a result; 58 with no instrument failure: 4 honoured, 4 violated, 50 with no contract checked; 31 where Syntology's instrument failed) · 59 unverified) and YOLO9000: Better, Faster, Stronger (arXiv:1612.08242; that paper's own run record: 44 ran (of which 0 constructed an object rather than computing a result; 33 with no instrument failure: 1 honoured, 4 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
chuanqichen/deepcoaching mentioned on GitHubpytorchSyntology: not harvested report
cokowpublic/Nuclei-Segmentation mentioned on GitHubSyntology: not harvested report
collectionslab/Omniscribe mentioned on GitHubpytorchSyntology: not harvested report
collectionslab/annotations-computervision mentioned on GitHubpytorchSyntology: not harvested report
collectionslab/book-annotation-classification mentioned on GitHubpytorchSyntology: not harvested report
crowdai/crowdai-mapping-challenge-mask-rcnn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
cwbabel/faster-cnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
delldu/MaskRCNN mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
deolipankaj/Stone_Detection_MRCNN mentioned on GitHubtfMITSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
devsoft123/fast-cnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
dvl-tum/motsynth-baselines mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
elonashatri/pitch_mask_rcnn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
evaristr/py-faster_rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
fdac18/ForensicImages mentioned on GitHubSyntology: not harvested report
fsafe/Capstone mentioned on GitHubpytorchSyntology: not harvested report
godspeedcurry/lung-nodule-detection mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
guanfuchen/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
harrybolingot/mymaskrcnn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
houssemjebari/Fruit-Detection mentioned on GitHubSyntology: not harvested report
infini8-13/MaskRCNN_tryout mentioned on GitHubSyntology: not harvested report
itsasimiqbal/SeBRe mentioned on GitHubtfMITSyntology: 6 samples, 6 ran (1 instrument-failed) · 0 unverified report
jasjeetIM/Mask-RCNN mentioned on GitHubSyntology: not harvested report
jhihan/rsna_pneumonia_detection mentioned on GitHubtfSyntology: not harvested report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2Syntology: 1 sample, 0 ran · 1 unverified report
jianing-sun/Mask-YOLO mentioned on GitHubtfSyntology: not harvested report
jklife3/maskrcnn-impl mentioned on GitHubtfSyntology: not harvested report
jodumagpi/Xray-ObjSep-v1 mentioned on GitHubpytorchSyntology: not harvested report
jooyounghun/AI-Team-5 mentioned on GitHubSyntology: not harvested report
jremillard/images-to-osm mentioned on GitHubtfMITSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
jylins/core-text mentioned on GitHubpytorchSyntology: not harvested report
kbardool/mrcnn3 mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
kdethoor/panoptictorch mentioned on GitHubpytorchSyntology: not harvested report
krantirk/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
leochangzliao/OPBM mentioned on GitHubNOASSERTIONSyntology: not harvested report
leonardhan1979/fasterRCNN mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
lichengunc/mask-faster-rcnn mentioned on GitHubpytorchSyntology: not harvested report
lincaiming/py-faster-rcnn-update mentioned on GitHubNOASSERTIONSyntology: not harvested report
lincaiming/py-faster-rcnn-windows mentioned on GitHubNOASSERTIONSyntology: not harvested report
lixiaolei1982/DenseNet-base-Mask-RCNN-for-Human-Pose-Estimation mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
longcw/roialign.pytorch mentioned on GitHubpytorchSyntology: not harvested report
louisyuzhe/car-damage-detector mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
ls5122/mask-rcnn mentioned on GitHubpytorchSyntology: not harvested report
lucylow/salty-wet-man mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
lukoucky/image_recommendation mentioned on GitHubSyntology: not harvested report
maxfrei750/DeepParticleNet mentioned on GitHubtfMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
maxfrei750/FibeR-CNN mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
miaohua1982/simple_fasterrcnn_pytorch mentioned on GitHubpytorchSyntology: not harvested report
mic-dkfz/medicaldetectiontoolkit mentioned on GitHubpytorchSyntology: not harvested report
mirzaevinom/data_science_bowl_2018 mentioned on GitHubtfSyntology: not harvested report
mstfakts/building-detection-maskrcnn mentioned on GitHubSyntology: not harvested report
multimodallearning/pytorch-mask-rcnn mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
nikhithakarennagari/1311 mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
nikhithakarennagari/Git mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
noelcodes/Mask_RCNN mentioned on GitHubSyntology: not harvested report
o-evgeny/MRCNN_DeepFashion2 mentioned on GitHubtfSyntology: not harvested report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
phtruongan/py-faster-rcnn-docker mentioned on GitHubNOASSERTIONSyntology: not harvested report
phykn/film-defect-detection mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
pj1920/mask-r-cnn mentioned on GitHubtfSyntology: not harvested report
polospeter/TensorFlow-Advanced-Techniques-Specialization mentioned on GitHubtfSyntology: not harvested report
pvdhove/owl-mask-rcnn mentioned on GitHubSyntology: not harvested report
qilei123/pyfasterrcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
qq330488563/TEST mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
quocdat32461997/Mask_RCNN mentioned on GitHubtfSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
ravenwritingdesk/py-faster-rcnn-master mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
raymon-tian/hourglass-facekeypoints-detection mentioned on GitHubpytorchSyntology: not harvested report
rh01/fast-rnn mentioned on GitHubcaffe2Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast R-CNN (arXiv:1504.08083; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
rh01/faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
rickyHong/py-faster-rcnn-repl mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
rickyHong/py-faster-rcnn-repl-cudnn5-support mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
saehan-choi/pixellib_auto_labelling mentioned on GitHubpytorchMITSyntology: not harvested report
samsh19/ML_project mentioned on GitHubpytorchSyntology: not harvested report
sbetageri/MaskRCNN mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
scolocke/Traffic_Sign_ID_GTSRB_GTSDB mentioned on GitHubtfSyntology: not harvested report
soulguy/Faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
ssanyachetwani/Fashion-Trend-Detection-and-Recommendation-Model mentioned on GitHubSyntology: not harvested report
stanleycelestin1/AirsimDetectron mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
sunhui1234/haha mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
sunqiangxtcsun/faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
tensorpack/tensorpack mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (arXiv:1511.06434; that paper's own run record: 128 ran (of which 61 constructed an object rather than computing a result; 111 with no instrument failure: 3 honoured, 0 violated, 108 with no contract checked; 17 where Syntology's instrument failed) · 91 unverified) and Improved Training of Wasserstein GANs (arXiv:1704.00028; that paper's own run record: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
tryolabs/luminoth mentioned on GitHubtfSyntology: not harvested report
vimalabs/VIMA mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VIMA: General Robot Manipulation with Multimodal Prompts (arXiv:2210.03094; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
waspinator/deep-learning-explorer mentioned on GitHubApache-2.0Syntology: 7 samples, 3 ran (0 instrument-failed) · 4 unverified report
xjnpark/ds mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
xunhen/py-faster-rcnn-wjc mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
xzabg/faster-rcnn-with-Caltech mentioned on GitHubNOASSERTIONSyntology: not harvested report
yangyucheng000/Mask-RCNN mentioned on GitHubmindsporeSyntology: not harvested report
yangyucheng000/maskrcnn_mobilenetv1 mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
yczhang1017/SSD_resnet_pytorch mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (4 instrument-failed) · 1 unverified report
yj-littlesky/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
ykasten/layered-neural-atlases mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Layered Neural Atlases for Consistent Video Editing (arXiv:2109.11418; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
yubaoliu/rds-slam mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM (arXiv:2007.11898; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zhangchi9/Airbus_Ship_Detection mentioned on GitHubSyntology: not harvested report
zhong110020/py-faster-rcnn mentioned on GitHubcaffe2NOASSERTIONSyntology: not harvested report
2023-MindSpore-1/ms-code-217 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-7 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code9 mindsporeSyntology: not harvested report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MindSpore-paper-code-2/code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
Okery/PyTorch-Simple-MaskRCNN pytorchSyntology: 20 samples, 11 ran (4 instrument-failed) · 9 unverified report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
RituYadav92/Radar-RGB-Attentive-Multimodal-Object-Detection tfMITSyntology: 12 samples, 10 ran (2 instrument-failed) · 2 unverified report
alexander-pv/maskrcnn_tf2 tfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
code-implementation1/Code9 mindsporeSyntology: not harvested report
facebookresearch/detectron2 pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Focal Loss for Dense Object Detection (arXiv:1708.02002; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified) and An Extendable, Efficient and Effective Transformer-based Object Detector (arXiv:2204.07962; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
facebookresearch/maskrcnn-benchmark pytorchMITSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
hellohaozheng/maskrcnn-mindspore mindsporeApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
muyistarsky/MaskRCNN mindsporeApache-2.0Syntology: not harvested report
open-edge-platform/training_extensions pytorchApache-2.0Syntology: not harvested report
tensorflow/models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
xiuyu0000/papers_with_examples mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. 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

140 samples harvested: 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
17ran · our draft was wrong
7ran; the contract check could not run
74ran
39unverified

Licence: 32 of the 140 samples are pointer only, meaning Syntology does not serve that copy's text. For 9 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 30 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

facebookresearch/detectron named in the paper 1 sample, 0 ran · 1 unverified
mask_rcnn_fcn_head_v1upXconvs detectron/modeling/mask_rcnn_heads.py unverified Apache-2.0 (permissive) · da6beb58fc126d80 · report
AKASH2907/bird-species-classification community (archive-listed) 9 samples, 6 ran (2 instrument-failed) · 3 unverified
compute_backbone_shapes in 12 papers mask_rcnn/mrcnn/model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fe2cec088a3329de · report fixture: signature config:Config/0/?, image_shape:tuple/1/int · returned ndarray · level recorded 2026-09-24
conv_block in 95 papers mask_rcnn/mrcnn/model.py ran; the contract check could not run (RAISES) MIT (permissive) · 719785e60bebf517 · report fixture: signature input_tensor:KerasTensor/0/float, kernel_size:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, strides:tuple/1/int, use_bias:bool/0/bool, train_bn:bool/0/bool · returned KerasTensor · level recorded 2026-09-24
f1_score in 121 papers evaluate.py ran fingerprinted MIT (permissive) · 7a27a90793b810e0 · report fixture: signature precision:float/0/float, recall:float/0/float · returned float64 · level recorded 2026-09-26
precision in 25 papers evaluate.py ran MIT (permissive) · 31724c8757cac523 · report fixture: signature matrix:ndarray/2/float · returned float32 · level recorded 2026-09-26
recall in 38 papers evaluate.py ran MIT (permissive) · 87da8aaee2f03982 · report fixture: signature matrix:ndarray/2/float · returned float32 · level recorded 2026-09-26
step_decay in 11 papers inception_resnet_v2_finetune.py ran fingerprinted MIT (permissive) · 5d33de7d64f4be74 · report fixture: signature epoch:int/0/int · returned float · level recorded 2026-09-26
identity_block in 32 papers mask_rcnn/mrcnn/model.py unverified MIT (permissive) · 28c3981539e97ab6 · report
precision in 25 papers inception_resnet_v2_finetune.py unverified MIT (permissive) · b0079394b94f6c41 · report
Biantian/MscProject community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
_get_iou_types MaskRCNN/engine.py ran · our draft was wrong no licence file found · pointer only · eb050d9cb7cc6d18 · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-22
ErikGDev/instance-segmentation community (archive-listed) 11 samples, 9 ran (6 instrument-failed) · 2 unverified
batched_nms in 29 papers detectron2/layers/nms.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 0df9d3b583fbc6cb · report fixture: signature boxes:Tensor/2/float, scores:Tensor/1/float, idxs:Tensor/1/int, iou_threshold:float/0/float · returned Tensor · level recorded 2026-09-24
convert_basic_c2_names in 46 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_bbox_to_z in 7 papers sort.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 90a45e51733f1779 · report fixture: signature bbox:ndarray/1/float · returned ndarray · level recorded 2026-09-22
convert_c2_detectron_names in 45 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · 52810b504f0d1066 · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
convert_x_to_bbox in 6 papers sort.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 45940bb4051db020 · report fixture: signature x:ndarray/1/float, score:float/0/float · returned ndarray · level recorded 2026-09-22
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
sort.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · d84d92dcfe0933de · report fixture: signature bb_test:ndarray/1/float, bb_gt:ndarray/1/float · returned float · level recorded 2026-09-24
pad_masks in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 406f84cf799ed34d · report fixture: signature masks:Tensor/3/float, padding:int/0/int · returned tuple · level recorded 2026-09-24
paste_mask_in_image_old in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · d03592674030077f · report fixture: signature mask:Tensor/2/float, box:Tensor/1/float, img_h:int/0/int, img_w:int/0/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
paste_masks_in_image in 20 papers detectron2/layers/mask_ops.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · f74abd7e1355f8cd · report fixture: signature masks:Tensor/3/float, boxes:SimpleBoxes/0/?, image_shape:tuple/1/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-25
batched_nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4845964b76bba6c5 · report
nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · d3fa37a000ad294d · report
NiravRaiyani/Mask-R-CNN-for-water-detection community (archive-listed) 1 sample, 0 ran · 1 unverified
ParallelModel Water/mrcnn/parallel_model.py unverified MIT (permissive) · 2b22fff2ccb067f5 · report
Qinhj07/ATOMCode community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PrRoIPool2D pytorch/prroi_pool/prroi_pool.py ran · metamorphic tier: deterministic MIT (permissive) · f9314701324398e9 · report fixture: returned PrRoIPool2D · level recorded 2026-09-22
SfTI-Robotics/ROS-label-node community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
find_mask_centre ros_colour_node.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · db138f55e11c9fcd · report fixture: signature mask:ndarray/2/int, color_image:ndarray/3/int · returned tuple · level recorded 2026-09-26
find_median_depth ros_colour_node.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · a977bdfb32032057 · report fixture: signature mask_area:int/0/int, num_median:int/0/int, histg:list/1/list · returned float · level recorded 2026-09-26
numpify ros_numpy/registry.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 78d7ffd52e1d220a · report
TuSimple/mx-maskrcnn community (archive-listed) 1 sample, 0 ran · 1 unverified
convert_context rcnn/utils/load_model.py unverified Apache-2.0 (permissive) · 85b0d97b5f005697 · report
alililia/ascend_maskrcnn_mobilenetv1 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
config_ export.py ran Apache-2.0 (permissive) · 9df462e1d230bc54 · report fixture: signature cfg:Config/0/? · returned Config · level recorded 2026-09-26
casiopa/Madrid_Rooftops community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Config in 46 papers mrcnn/config.py ran no licence file found · pointer only · 999f238aed35c849 · report fixture: returned NoneType · level recorded 2026-09-24
charlesshang/fastmaskrcnn community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
assign_boxes libs/layers/assign.py ran Apache-2.0 (permissive) · d419a20996a55b4d · report fixture: signature gt_boxes:ndarray/2/float, min_k:int/0/int, max_k:int/0/int · returned ndarray · level recorded 2026-09-26
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
libs/layers/crop.py ran Apache-2.0 (permissive) · db26edf48d62a11f · report fixture: signature images:EagerTensor/4/float, boxes:EagerTensor/2/float, batch_inds:EagerTensor/1/int, stride:int/0/int, pooled_height:int/0/int, pooled_width:int/0/int, scope:str/0/str · returned EagerTensor · level recorded 2026-09-26
crop_ libs/layers/crop.py ran Apache-2.0 (permissive) · 5c3346882f6aec8d · report fixture: signature images:EagerTensor/4/float, boxes:EagerTensor/2/float, batch_inds:EagerTensor/1/int, ih:int/0/int, iw:int/0/int, stride:int/0/int, pooled_height:int/0/int, pooled_width:int/0/int, scope:str/0/str · returned list · level recorded 2026-09-26
memory_timeline libs/memory_util.py ran Apache-2.0 (permissive) · cad4fcfbbe116ec2 · report fixture: signature log:str/0/str · returned list · level recorded 2026-09-26
my_sigmoid libs/nets/pyramid_network.py ran fingerprinted Apache-2.0 (permissive) · 48d1ea0deabb6bfd · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
peak_memory libs/memory_util.py ran Apache-2.0 (permissive) · a164f194df88e3d7 · report fixture: signature log:StringIO/0/? · returned int · level recorded 2026-09-26
anchor_decoder libs/layers/wrapper.py unverified Apache-2.0 (permissive) · a32721bd950d81bc · report
anchor_encoder libs/layers/wrapper.py unverified Apache-2.0 (permissive) · c36aeb8be319786c · report
roi_encoder libs/layers/wrapper.py unverified Apache-2.0 (permissive) · d65eef69ba777b63 · report
smart_initialize libs/memory_util.py unverified Apache-2.0 (permissive) · 5054e9f6388175ac · report
chenwuperth/ClaRAN community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
box_to_point8 common.py ran fingerprinted Apache-2.0 (permissive) · 59b659c3eb365fb3 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-26
point8_to_box common.py ran fingerprinted Apache-2.0 (permissive) · e99bbed8ef483eba · report fixture: signature points:ndarray/2/float · returned ndarray · level recorded 2026-09-24
freeze_affine_getter basemodel.py unverified Apache-2.0 (permissive) · 69d5512d768ea9dd · report
segmentation_to_mask common.py unverified Apache-2.0 (permissive) · 72f76b2aba37ad06 · report
deolipankaj/Stone_Detection_MRCNN community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
color_splash samples/stone/stone.py ran MIT (permissive) · 191fdaa5da6fdd3a · report fixture: signature image:ndarray/3/int, mask:ndarray/3/float · returned ndarray · level recorded 2026-09-26
compute_overlaps in 11 papers mrcnn/utils.py ran · honoured contract fingerprinted MIT (permissive) · 9f81af6c8a2344a3 · report fixture: signature boxes1:ndarray/2/float, boxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
extract_bboxes in 14 papers mrcnn/utils.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d2c9b72e23d9588a · report fixture: signature mask:ndarray/3/int · returned ndarray · level recorded 2026-09-24
mask_to_rle samples/nucleus/nucleus.py ran MIT (permissive) here; the stored copy is pointer only · 268687f4c9e090fd · report fixture: signature image_id:str/0/str, mask:ndarray/3/int, scores:ndarray/1/float · returned str · level recorded 2026-09-24
rle_encode in 6 papers samples/nucleus/nucleus.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 4ea804a726823d02 · report fixture: signature mask:ndarray/2/int · returned str · level recorded 2026-09-24
rle_decode in 5 papers samples/nucleus/nucleus.py unverified MIT (permissive) here; the stored copy is pointer only · 369cf3a7e608d9c5 · report
dvl-tum/motsynth-baselines community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
maskrcnn_resnet_fpn src/detection/maskrcnn.py ran · our draft was wrong MIT (permissive) · 3e0cbc427f82679b · report fixture: signature backbone_name:str/0/str, pretrained:bool/0/bool, num_classes:int/0/int, pretrained_backbone:bool/0/bool, trainable_backbone_layers:NoneType/0/? · returned MaskRCNN · level recorded 2026-09-22
itsasimiqbal/SeBRe community (archive-listed) 6 samples, 6 ran (1 instrument-failed) · 0 unverified
compute_iou in 68 papers utils.py ran MIT (permissive) · b2aae18de5fa3893 · report fixture: signature box:ndarray/1/float, boxes:ndarray/2/float, box_area:float/0/float, boxes_area:ndarray/1/float · returned ndarray · level recorded 2026-09-25
compute_overlaps in 11 papers utils.py ran fingerprinted MIT (permissive) · 698f3241ee39ad75 · report fixture: signature boxes1:ndarray/2/float, boxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-25
conv_block in 95 papers model.py ran MIT (permissive) · f998b7fc598210b3 · report fixture: signature input_tensor:KerasTensor/0/float, kernel_size:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, strides:tuple/1/int, use_bias:bool/0/bool · returned KerasTensor · level recorded 2026-09-25
get_ax in 5 papers visualize.py ran · our draft was wrong MIT (permissive) · e0532d01052a38df · report fixture: signature rows:int/0/int, cols:int/0/int, size:int/0/int · returned ndarray · level recorded 2026-09-24
identity_block in 32 papers model.py ran MIT (permissive) · 572ccdbc1739d878 · report fixture: signature input_tensor:KerasTensor/0/float, kernel_size:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, use_bias:bool/0/bool · returned KerasTensor · level recorded 2026-09-25
resnet_graph model.py ran MIT (permissive) · 5883d43b9e07bf2e · report fixture: signature input_image:KerasTensor/4/float, architecture:str/0/str, stage5:bool/0/bool · returned list · level recorded 2026-09-25
jiajunhua/facebookresearch-Detectron community (archive-listed) 1 sample, 0 ran · 1 unverified
add_mask_rcnn_outputs detectron/modeling/mask_rcnn_heads.py unverified Apache-2.0 (permissive) · f2feef6e5d418be2 · report
jremillard/images-to-osm community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
condition QuadKey/quadkey/util.py ran MIT (permissive) · 5b9547b968ed893e · report fixture: signature precondition:callable/0/?, postcondition:callable/0/? · returned function · level recorded 2026-09-26
get_ax in 5 papers train_shapes.py ran MIT (permissive) · 8cfb49cfabce52c6 · report fixture: signature rows:int/0/int, cols:int/0/int, size:int/0/int · returned ndarray · level recorded 2026-09-26
makeOsmFileName createfinalosm.py ran fingerprinted MIT (permissive) · 7787db1a5c010d9c · report fixture: signature fileNumber:int/0/int · returned str · level recorded 2026-09-26
postcondition QuadKey/quadkey/util.py ran MIT (permissive) · f37cd312a3221c9c · report fixture: signature check:callable/0/? · returned function · level recorded 2026-09-26
precondition QuadKey/quadkey/util.py ran MIT (permissive) · f9eb51afeae50a09 · report fixture: signature check:callable/0/? · returned function · level recorded 2026-09-26
toDegrees createosmanomaly.py ran fingerprinted MIT (permissive) · 36ff0a65b81a05c7 · report fixture: signature rad:float/0/float · returned float · level recorded 2026-09-26
valid_level QuadKey/quadkey/tile_system.py ran fingerprinted MIT (permissive) · 0cb39a05c3ca5bc5 · report fixture: signature level:int/0/int · returned bool · level recorded 2026-09-26
maxfrei750/DeepParticleNet community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
calculate_equivalent_diameter dpn/utilities.py ran fingerprinted MIT (permissive) · b0552e0cd657d297 · report fixture: signature areas:list/1/float · returned list · level recorded 2026-09-26
get_axis dpn/visualize.py ran MIT (permissive) · 9ba88f2169cec310 · report fixture: signature rows:int/0/int, cols:int/0/int, size:int/0/int · returned ndarray · level recorded 2026-09-26
get_major_bbox_side_length dpn/utilities.py ran fingerprinted MIT (permissive) · e035b60ab83add6c · report fixture: signature bboxes:ndarray/2/float · returned list · level recorded 2026-09-26
get_maximum_feret_diameter dpn/utilities.py ran MIT (permissive) · e27952fa526b4d8f · report fixture: signature masks:list/1/ndarray · returned list · level recorded 2026-09-26
display_instance_outlines dpn/visualize.py unverified MIT (permissive) · 4a383941db4ad33c · report
plot_size_distributions dpn/visualize.py unverified MIT (permissive) · 73a188fb561561b3 · report
maxfrei750/FibeR-CNN community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
euclidean_distance in 29 papers fibercnn/modeling/losses.py ran fingerprinted MIT (permissive) · 4ec42dd9d2a8b00f · report fixture: signature pt1:Tensor/1/float, pt2:Tensor/1/float · returned Tensor · level recorded 2026-09-26
frechet_distance in 9 papers fibercnn/modeling/losses.py ran MIT (permissive) · 1c40c7b937c2dee3 · report fixture: signature P:Tensor/2/float, Q:Tensor/2/float, device:str/0/str · returned Tensor · level recorded 2026-09-26
spline_interpolation data_preparation/spline_utilities.py ran MIT (permissive) · 5b582864bbb4e8ae · report fixture: signature keypoints:ndarray/2/float, num_interpolation_steps:int/0/int · returned ndarray · level recorded 2026-09-26
spline_to_mask data_preparation/spline_utilities.py ran MIT (permissive) · 84dcf50f99ab0ecf · report fixture: signature image_size:tuple/1/int, key_points:ndarray/2/float, width:int/0/int, num_interpolation_steps:int/0/int · returned Image · level recorded 2026-09-26
phykn/film-defect-detection community (archive-listed) 1 sample, 0 ran · 1 unverified
MASK_MODEL module/model.py unverified no licence file found · pointer only · 7d2a70befdcc79e1 · report
quocdat32461997/Mask_RCNN community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
ROIAlign models/mask_rcnn.py ran MIT (permissive) · 2923771eb82a595b · report fixture: signature features:EagerTensor/4/float, regions:EagerTensor/3/float, scores:EagerTensor/3/float · returned tuple · level recorded 2026-09-24
ResNet in 139 papers models/mask_rcnn.py ran fingerprinted MIT (permissive) · 2f5268f616a76ae8 · report fixture: returned ResNet · level recorded 2026-09-22
MaskRCNN models/mask_rcnn.py unverified MIT (permissive) · d4e2ba081488d580 · report
ProposalLayer models/mask_rcnn.py unverified MIT (permissive) · 5e8363cd23751330 · report
sbetageri/MaskRCNN community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
calcBoundingBoxParams Utils.py ran MIT (permissive) · a22a6a153ea702d8 · report fixture: signature bbox:tuple/1/float, anchorBBox:tuple/1/float · returned tuple · level recorded 2026-09-26
getBoundingBoxes Utils.py ran MIT (permissive) · 758f01cfe36c9503 · report fixture: signature annotations:list/1/dict · returned list · level recorded 2026-09-26
openImage Utils.py ran MIT (permissive) · 9c8e4cb9c9be913a · report fixture: signature imgPath:str/0/str · returned PngImageFile · level recorded 2026-09-26
stanleycelestin1/AirsimDetectron community (archive-listed) 1 sample, 0 ran · 1 unverified
add_mask_rcnn_outputs detectron/modeling/mask_rcnn_heads.py unverified licence not identified · pointer only · 59d6f2ed8f252aa2 · report
waspinator/deep-learning-explorer community (archive-listed) 7 samples, 3 ran (0 instrument-failed) · 4 unverified
compute_backbone_shapes in 12 papers mask-rcnn/libraries/mrcnn/model.py ran Apache-2.0 (permissive) · e109baa006f999cb · report fixture: signature config:Config/0/?, image_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
conv_block in 95 papers mask-rcnn/libraries/mrcnn/model.py ran Apache-2.0 (permissive) · 918c5de88a445168 · report fixture: signature input_tensor:KerasTensor/0/float, kernel_size:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, strides:tuple/1/int, use_bias:bool/0/bool, train_bn:bool/0/bool · returned KerasTensor · level recorded 2026-09-25
fcn_resnet50_imagenet_weights_path semantic-segmentation/libraries/semantic/models.py ran fingerprinted Apache-2.0 (permissive) · 170625e697451c36 · report fixture: signature cache_dir:str/0/str · returned str · level recorded 2026-09-26
binary_crossentropy_with_logits semantic-segmentation/libraries/semantic/losses.py unverified Apache-2.0 (permissive) · d91391a07c73bc41 · report
identity_block in 32 papers mask-rcnn/libraries/mrcnn/model.py unverified Apache-2.0 (permissive) · b2617f9b70d02ce1 · report
resnet50_imagenet_weights_path semantic-segmentation/libraries/semantic/models.py unverified Apache-2.0 (permissive) · c86c8738f440e32d · report
softmax_sparse_crossentropy_ignoring_last_label semantic-segmentation/libraries/semantic/losses.py unverified Apache-2.0 (permissive) · 08657af272d389cf · report
yczhang1017/SSD_resnet_pytorch community (archive-listed) 8 samples, 7 ran (4 instrument-failed) · 1 unverified
intersect in 33 papers layers/box_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · f01c5f73515770a5 · report fixture: signature box_a:Tensor/2/float, box_b:Tensor/2/float · returned Tensor · level recorded 2026-09-22
intersect in 33 papers utils/augmentations.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 6ec11ee890696819 · report fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-24
jaccard_numpy in 7 papers utils/augmentations.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 13675bf1f3f88001 · report fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-24
make_layers in 155 papers ssd.py ran MIT (permissive) · 87879670fa899706 · report fixture: signature block:callable/0/?, inplanes:int/0/int, planes:int/0/int, blocks:int/0/int, stride:int/0/int · returned list · level recorded 2026-09-26
point_form in 15 papers layers/box_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 3bea1addc1e14162 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-22
resnet in 17 papers ssd.py ran MIT (permissive) · d0fe9575507d3512 · report fixture: returned list · level recorded 2026-09-26
vgg in 16 papers ssd.py ran MIT (permissive) · ffaa53645a656dd0 · report fixture: signature cfg:list/1/int, i:int/0/int, batch_norm:bool/0/bool · returned list · level recorded 2026-09-26
center_size in 14 papers layers/box_utils.py unverified MIT (permissive) · aa1d78402838820a · report
Okery/PyTorch-Simple-MaskRCNN community (archive-listed) 20 samples, 11 ran (4 instrument-failed) · 9 unverified
AnchorGenerator pytorch_mask_rcnn/model/mask_rcnn.py ran MIT (permissive) · 1325bdc51f31c55d · report fixture: signature feature:Tensor/4/float, image_size:tuple/1/int · returned Tensor · level recorded 2026-09-24
BalancedPositiveNegativeSampler pytorch_mask_rcnn/model/mask_rcnn.py ran fingerprinted MIT (permissive) · f7fc8874ef491d1b · report fixture: signature label:Tensor/1/int · returned tuple · level recorded 2026-09-24
BoxCoder pytorch_mask_rcnn/model/mask_rcnn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 1c7d7c29761bd504 · report fixture: signature reference_box:Tensor/2/float, proposal:Tensor/2/float · returned Tensor · level recorded 2026-09-22
FastRCNNPredictor pytorch_mask_rcnn/model/mask_rcnn.py ran fingerprinted MIT (permissive) · b3e07db8b30c86d9 · report fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-24
MaskRCNNPredictor pytorch_mask_rcnn/model/mask_rcnn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · cd857827be084259 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
RPNHead pytorch_mask_rcnn/model/mask_rcnn.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · fad9d2935c3035e5 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
box_iou in 34 papers pytorch_mask_rcnn/model/mask_rcnn.py ran · our draft was wrong fingerprinted MIT (permissive) · 46c0d05b31f0858a · report fixture: signature box_a:Tensor/2/float, box_b:Tensor/2/float · returned Tensor · level recorded 2026-09-22
expand_detection pytorch_mask_rcnn/model/mask_rcnn.py ran · our draft was wrong fingerprinted MIT (permissive) · 058977fec9eddec0 · report fixture: signature mask:Tensor/2/float, box:Tensor/2/float, padding:int/0/int · returned tuple · level recorded 2026-09-22
paste_masks_in_image in 20 papers pytorch_mask_rcnn/model/mask_rcnn.py ran MIT (permissive) · 5a9465666961697d · report fixture: signature mask:Tensor/3/float, box:Tensor/2/float, padding:int/0/int, image_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
process_box pytorch_mask_rcnn/model/mask_rcnn.py ran · our draft was wrong fingerprinted MIT (permissive) · be6875790c66649a · report fixture: signature box:Tensor/2/float, score:Tensor/1/float, image_shape:tuple/1/int, min_size:int/0/int · returned tuple · level recorded 2026-09-22
roi_align pytorch_mask_rcnn/model/mask_rcnn.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · b763ac756dce21c1 · report fixture: signature features:Tensor/4/float, rois:Tensor/2/float, spatial_scale:float/0/float, pooled_height:int/0/int, pooled_width:int/0/int, sampling_ratio:int/0/int · returned Tensor · level recorded 2026-09-22
MaskRCNN pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · af488128bb90c8f8 · report
Matcher pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · 56e38f0f416967d3 · report
RegionProposalNetwork pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · 053c71cb990c78af · report
RoIAlign pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · 7077f9ecfc218271 · report
RoIHeads pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · cecaeaf6a683e156 · report
Transformer in 173 papers pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · 9bd9f8474a0c4ed4 · report
fastrcnn_loss pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · 1e30107c9c44b318 · report
maskrcnn_loss pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · b1cf58a0e5e155d3 · report
nms in 65 papers pytorch_mask_rcnn/model/mask_rcnn.py unverified MIT (permissive) · 149eabaf3e4ba32b · report
RituYadav92/Radar-RGB-Attentive-Multimodal-Object-Detection community (archive-listed) 12 samples, 10 ran (2 instrument-failed) · 2 unverified
apply_mask in 25 papers Radar_RGB_Camera_Object_Detection/mrcnn/visualize.py ran MIT (permissive) · cdda836085a5b1af · report fixture: signature image:ndarray/3/float, mask:ndarray/2/int, color:ndarray/1/float, alpha:float/0/float · returned ndarray · level recorded 2026-09-24
build_coco_results Radar_RGB_Camera_Object_Detection/coco/nucoco.py ran MIT (permissive) · 7f280eb4a7351f25 · report fixture: signature dataset:MockDataset/0/?, image_ids:list/1/int, rois:ndarray/2/float, class_ids:ndarray/1/int, scores:ndarray/1/float · returned list · level recorded 2026-09-26
compute_backbone_shapes in 12 papers Radar_RGB_Camera_Object_Detection/mrcnn/model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · ae91aee49740c295 · report fixture: signature config:StandInConfig/0/?, image_shape:tuple/1/int · returned ndarray · level recorded 2026-09-22
compute_iou in 68 papers Radar_RGB_Camera_Object_Detection/mrcnn/utils.py ran · violated contract MIT (permissive) · ae0c5e015d8cf734 · report fixture: signature box:ndarray/1/float, boxes:ndarray/2/float, box_area:float/0/float, boxes_area:ndarray/1/float · returned ndarray · level recorded 2026-09-24
compute_overlaps in 11 papers Radar_RGB_Camera_Object_Detection/mrcnn/utils.py ran fingerprinted MIT (permissive) · ce35a8bfbf575240 · report fixture: signature boxes1:ndarray/2/float, boxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-26
draw_box in 16 papers Radar_RGB_Camera_Object_Detection/mrcnn/visualize.py ran · our draft was wrong MIT (permissive) · dc05d22f3d39bea6 · report fixture: signature image:ndarray/3/int, box:tuple/1/int, color:list/1/int · returned ndarray · level recorded 2026-09-24
extract_bbox_boxes Radar_RGB_Camera_Object_Detection/mrcnn/utils.py ran MIT (permissive) · f5f8fd02f09d1b8a · report fixture: signature bbox:ndarray/3/bool · returned ndarray · level recorded 2026-09-26
get_ax in 5 papers Radar_RGB_Camera_Object_Detection/coco/nucoco.py ran MIT (permissive) · 41b8f24cef813f2d · report fixture: signature rows:int/0/int, cols:int/0/int, size:int/0/int · returned ndarray · level recorded 2026-09-26
random_colors in 12 papers Radar_RGB_Camera_Object_Detection/mrcnn/visualize.py ran · honoured contract MIT (permissive) · a9d0cf3b71fefa32 · report fixture: signature N:int/0/int, bright:bool/0/bool · returned list · level recorded 2026-09-24
spatial_squeeze_excite_block Radar_RGB_Camera_Object_Detection/mrcnn/se.py ran MIT (permissive) · 9db0cd3de6838b93 · report fixture: signature input_tensor:KerasTensor/0/float · returned KerasTensor · level recorded 2026-09-26
channel_spatial_squeeze_excite Radar_RGB_Camera_Object_Detection/mrcnn/se.py unverified MIT (permissive) · 5e9a82d8b587ab4d · report
squeeze_excite_block Radar_RGB_Camera_Object_Detection/mrcnn/se.py unverified MIT (permissive) · b58adb85306dbb43 · report
alexander-pv/maskrcnn_tf2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MaskRCNN src/model.py ran licence not identified · pointer only · 690138ef9c4b53a9 · report fixture: returned MaskRCNN · level recorded 2026-09-22
facebookresearch/maskrcnn-benchmark community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
get_group_gn in 5 papers maskrcnn_benchmark/modeling/make_layers.py ran MIT recorded; this copy not marked cleared · pointer only · 83c64313d0501174 · report fixture: signature dim:int/0/int, dim_per_gp:int/0/int, num_groups:int/0/int · returned int · level recorded 2026-09-25
interpolate in 95 papers maskrcnn_benchmark/layers/misc.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 2902bf4410253ff7 · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-25
sigmoid_focal_loss_cpu in 18 papers maskrcnn_benchmark/layers/sigmoid_focal_loss.py ran MIT recorded; this copy not marked cleared · pointer only · c42eaa8eb1b704cd · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/int, gamma:float/0/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-24
smooth_l1_loss in 28 papers maskrcnn_benchmark/layers/smooth_l1_loss.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · e261fa29066b37e5 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, beta:float/0/float, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-24
hellohaozheng/maskrcnn-mindspore community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
bbox_overlaps in 20 papers dataset/dataset.py ran Apache-2.0 (permissive) · 877a057aa182bb54 · report fixture: signature bboxes1:ndarray/2/int, bboxes2:ndarray/2/int, mode:str/0/str · returned ndarray · level recorded 2026-09-26
get_ax in 5 papers infer.py ran Apache-2.0 (permissive) · 9bac464cd3083481 · report fixture: signature rows:int/0/int, cols:int/0/int, size:int/0/int · returned ndarray · level recorded 2026-09-26
rescale_with_factor dataset/dataset.py ran fingerprinted Apache-2.0 (permissive) · 17af8ddb252d42d2 · report fixture: signature img:ndarray/3/int, scale_factor:float/0/float · returned ndarray · level recorded 2026-09-26
rescale_with_tuple dataset/dataset.py ran Apache-2.0 (permissive) · 024188cefd019662 · report fixture: signature img:ndarray/3/int, scale:tuple/1/int · returned tuple · level recorded 2026-09-26

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

12 assemblies on this paper: 12 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

12 sibling assemblies for Mask R-CNN (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. maskrcnn_resnet_fpn entry · level 1 · ran · our draft was wrong · 3e0cbc427f82679b

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 4 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. MaskRCNN entry · level 0 · unverified · d4e2ba081488d580
  2. ProposalLayer helper · level 0 · unverified · 5e8363cd23751330
  3. ROIAlign model · level 1 · ran · 2923771eb82a595b
  4. ResNet model · level 1 · ran · 2f5268f616a76ae8

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. _get_iou_types entry · level 1 · ran · our draft was wrong · eb050d9cb7cc6d18

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 12 siblings

  1. PrRoIPool2D entry · level 1 · ran · f9314701324398e9
  2. PrRoIPool2DFunction helper · level 1 · ran · 09437f377453bac2
  3. _import_prroi_pooling helper · level 0 · unverified · 3e242db47ba04fed

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. ParallelModel entry · level 0 · unverified · 2b22fff2ccb067f5

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 12 siblings

  1. MaskRCNN entry · level 1 · ran · 690138ef9c4b53a9

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. add_mask_rcnn_outputs entry · level 0 · unverified · 59d6f2ed8f252aa2
  2. const_fill helper · level 1 · ran · our draft was wrong · 93f6fc328f31783a
  3. gauss_fill helper · level 1 · ran · our draft was wrong · 1e455c239bf7bdd6
  4. AttrDict helper · level 0 · unverified · 5904b95e70b5177a

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. mask_rcnn_fcn_head_v1upXconvs entry · level 0 · unverified · da6beb58fc126d80
  2. const_fill helper · level 1 · ran · our draft was wrong · 93f6fc328f31783a
  3. AttrDict helper · level 0 · unverified · 5904b95e70b5177a

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. Config entry · level 1 · ran · 999f238aed35c849

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 20 bricks; individually on a fixture: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. MaskRCNN entry · level 0 · unverified · af488128bb90c8f8
  2. AnchorGenerator helper · level 1 · ran · 1325bdc51f31c55d
  3. FastRCNNPredictor model · level 1 · ran · b3e07db8b30c86d9
  4. MaskRCNNPredictor model · level 1 · ran · cd857827be084259
  5. RPNHead helper · level 1 · ran · fad9d2935c3035e5
  6. RegionProposalNetwork model · level 0 · unverified · 053c71cb990c78af
  7. RoIAlign model · level 0 · unverified · 7077f9ecfc218271
  8. RoIHeads model · level 0 · unverified · cecaeaf6a683e156
  9. Transformer helper · level 0 · unverified · 9bd9f8474a0c4ed4
  10. BalancedPositiveNegativeSampler helper · level 1 · ran · f7fc8874ef491d1b
  11. BoxCoder helper · level 1 · ran · 1c7d7c29761bd504
  12. Matcher helper · level 0 · unverified · 56e38f0f416967d3
  13. box_iou helper · level 1 · ran · our draft was wrong · 46c0d05b31f0858a
  14. nms helper · level 0 · unverified · 149eabaf3e4ba32b
  15. process_box helper · level 1 · ran · our draft was wrong · be6875790c66649a
  16. roi_align helper · level 1 · ran; the contract check could not run (RAISES) · b763ac756dce21c1
  17. fastrcnn_loss helper · level 0 · unverified · 1e30107c9c44b318
  18. maskrcnn_loss helper · level 0 · unverified · b1cf58a0e5e155d3
  19. paste_masks_in_image helper · level 1 · ran · 5a9465666961697d
  20. expand_detection helper · level 1 · ran · our draft was wrong · 058977fec9eddec0

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. MASK_MODEL entry · level 0 · unverified · 7d2a70befdcc79e1

harvested Assembly for Mask R-CNN (graph method: Mask R-CNN). 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 12 siblings

  1. add_mask_rcnn_outputs entry · level 0 · unverified · f2feef6e5d418be2
  2. const_fill helper · level 1 · ran · our draft was wrong · 93f6fc328f31783a
  3. gauss_fill helper · level 1 · ran · our draft was wrong · 1e455c239bf7bdd6
  4. AttrDict helper · level 0 · unverified · 5904b95e70b5177a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1703.06870") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Instance SegmentationHuman Part SegmentationInstance SegmentationKeypoint DetectionKeypoint EstimationMulti-Human ParsingMulti-Person Pose EstimationMulti-tissue Nucleus SegmentationNuclear SegmentationObjectObject DetectionObject LocalizationObject SegmentationPanoptic SegmentationPose EstimationReal-Time Object DetectionSegmentationSemantic Segmentation

Datasets

Introduced by this paper, per the archive.

PRID2011

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation BDD100K val Mask R-CNN AP 20.5 #3 of 4 Archive leaderboard report
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) AP50 60.0 #93 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) AP75 39.4 #93 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) APL 53.5 #93 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) APM 39.9 #93 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) APS 16.9 #93 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Mask R-CNN (ResNeXt-101-FPN) mask AP 37.1 #93 of 112 Archive leaderboard report
Instance Segmentation iSAID Mask-RCNN+ Average Precision 37.18 #3 of 5 Archive leaderboard report
Instance Segmentation iSAID Mask-RCNN Average Precision 36.50 #4 of 5 Archive leaderboard report
Keypoint Detection COCO Mask R-CNN Test AP 63.1 #1 of 2 Archive leaderboard report
Keypoint Detection COCO Mask R-CNN Validation AP 69.2 #1 of 2 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* AP 68.9 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* AP50 89.2 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* AP75 75.2 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* APL 82.6 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* AR 75.4 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* AR50 93.2 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* AR75 81.2 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* ARL 76.8 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Mask R-CNN* ARM 70.2 #5 of 8 Archive leaderboard report
Keypoint Detection COCO test-dev Mask R-CNN AP50 87.3 #14 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Mask R-CNN AP75 68.7 #14 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Mask R-CNN APL 71.4 #14 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Mask R-CNN APM 57.8 #14 of 16 Archive leaderboard report
Multi-Human Parsing MHP v1.0 Mask R-CNN AP 0.5 52.68% #2 of 4 Archive leaderboard report
Multi-Human Parsing MHP v2.0 Mask R-CNN AP 0.5 14.9 #5 of 5 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Mask R-CNN AP Easy 69.4 #25 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Mask R-CNN AP Hard 45.8 #25 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Mask R-CNN AP Medium 57.9 #25 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Mask R-CNN mAP @0.5:0.95 57.2 #25 of 28 Archive leaderboard report
Multi-Person Pose Estimation OCHuman Mask R-CNN AP50 33.2 #8 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman Mask R-CNN AP75 24.5 #8 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman Mask R-CNN Validation AP 20.2 #8 of 8 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar Mask R-CNN (e) Dice 0.760 #17 of 18 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar Mask R-CNN (e) Hausdorff Distance (mm) 50.9 #17 of 18 Archive leaderboard report
Nuclear Segmentation Cell17 Mask R-CNN Dice 0.707 #2 of 4 Archive leaderboard report
Nuclear Segmentation Cell17 Mask R-CNN F1-score 0.8004 #2 of 4 Archive leaderboard report
Nuclear Segmentation Cell17 Mask R-CNN Hausdorff 12.6723 #2 of 4 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-101-FPN) box AP 40.0 #184 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN) box AP 37.7 #202 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNeXt-101-FPN) AP50 59.5 #204 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNeXt-101-FPN) AP75 38.9 #204 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNeXt-101-FPN) box AP 36.7 #204 of 220 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) AP50 62.3 #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) AP75 43.4 #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) APL 51.2 #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) APM 43.2 #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) APS 22.1 #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) Hardware Burden 9G #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNeXt-101-FPN) box mAP 39.8 #199 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) AP50 60.3 #212 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) AP75 41.7 #212 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) APL 50.2 #212 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) APM 41.1 #212 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) APS 20.1 #212 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) Hardware Burden 9G #212 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN) box mAP 38.2 #212 of 225 Archive leaderboard report
Object Detection COCO-O Mask R-CNN (ResNet-50) Average mAP 17.1 #35 of 45 Archive leaderboard report
Object Detection COCO-O Mask R-CNN (ResNet-50) Effective Robustness -0.11 #45 of 45 Archive leaderboard report
Object Detection iSAID Mask-RCNN+ Average Precision 37.18 #4 of 5 Archive leaderboard report
Object Detection iSAID Mask-RCNN Average Precision 36.50 #5 of 5 Archive leaderboard report
Object Localization GRIT Mask R-CNN Localization (ablation) 44.7 #3 of 3 Archive leaderboard report
Object Localization GRIT Mask R-CNN Localization (test) 45.1 #3 of 3 Archive leaderboard report
Object Segmentation GRIT Mask R-CNN Segmentation (ablation) 26.2 #2 of 2 Archive leaderboard report
Object Segmentation GRIT Mask R-CNN Segmentation (test) 26.2 #2 of 2 Archive leaderboard report
Panoptic Segmentation Cityscapes val Mask R-CNN+COCO PQth 54.0 #37 of 37 Archive leaderboard report
Pose Estimation COCO test-dev Mask-RCNN AP 63.1 #43 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Mask-RCNN AP50 87.3 #43 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Mask-RCNN AP75 68.7 #43 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Mask-RCNN APL 71.4 #43 of 47 Archive leaderboard report
Real-Time Object Detection COCO Mask R-CNN X-152-32x8d box AP 45.2 #1 of 1 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: Mask R-CNN, RoIAlign

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationMask R-CNNMax PoolingRPNReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIAlignSoftmax

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