vision
Mask R-CNN
Extends Faster R-CNN with a mask branch for instance segmentation; the reference instance segmentation model in Detectron2 and MMDetection.
Levelvariant
Classvision
Parametersnot in the notes
Contextnot in the notes
Released20 Mar 2017
Opennessunknown
Runs onmobile or NPU, CPU server
Statusactive
Identity
- Developer
- Meta
- Family
- R-CNN family
- Released
- 20 Mar 2017 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- CNN
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- R50, R101, X101, X152, LVIS long-tail, Swin-T and LSJ schedules in Detectron2, MMDetection, TorchVision, TF Model Garden and NVIDIA DLE.
- Context length
- not in the notes
- Input
- image
- Output
- image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU, CPU server
- Footprint
- Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperMetabig tech, USA
Metabig tech, USAModelMask R-CNNMeta, vision
Mask R-CNNMeta, visionUse CasesMedical Image SegmentationHealthcareRobotic Waste and Recycling SortingIndustrialUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Organisations 1
Sources
- arxiv.org/abs/1703.06870 https://arxiv.org/abs/1703.06870
- jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
- aihub.qualcomm.com/models/maskrcnn https://aihub.qualcomm.com/models/maskrcnn
- github.com/pytorch/vision https://github.com/pytorch/vision
- github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/mask_rcnn_inception_resnet_v2_atrous_coco
- huggingface.co/OpenVINO/maskrcnn_r50-fp16-ov https://huggingface.co/OpenVINO/maskrcnn_r50-fp16-ov
- catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/maskrcnn__pyt_ckpt https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/maskrcnn__pyt_ckpt
- arxiv.org/html/1703.06870 https://arxiv.org/html/1703.06870
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Mask R-CNN", https://aurion.semai.id/models/mask-r-cnn/, records of October 2026.