Project AURIONAI Use-Cases Research & Innovation
Meta
vision

MaskFormer

Meta mask classification model for semantic and panoptic segmentation, from the paper "Per-Pixel Classification is Not All You Need".

MetaMetaUSA
Diagram of MaskFormer pixel-level, transformer and segmentation modules, from the model card.
Levelmodel
Classvision
Parameters41.78M
Contextnot in the notes
Released13 Jul 2021
Opennessopen weights restricted
Runs onnot in the notes
Statusactive

R&D Topics

Semantic, instance and panoptic segmentation architecturesproduced by

Identity

Developer
Meta
Family
not in the notes
Released
13 Jul 2021 sourcesannouncement page
Weights published
2 Mar 2022
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
dense transformer
Total parameters
41.78M sources
Active parameters
–
Checkpoint parameters
–
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
open weights restricted
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
not in the notes
Footprint
not in the notes
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.

Sources

  1. arxiv.org/abs/2107.06278 https://arxiv.org/abs/2107.06278
  2. huggingface.co/facebook/maskformer-swin-tiny-coco https://huggingface.co/facebook/maskformer-swin-tiny-coco
  3. ai.azure.com/catalog/models?task=image-segmentation https://ai.azure.com/catalog/models?task=image-segmentation
  4. github.com/open-mmlab/mmdetection/tree/main/configs/mask... https://github.com/open-mmlab/mmdetection/tree/main/configs/maskformer
  5. github.com/facebookresearch/MaskFormer https://github.com/facebookresearch/MaskFormer

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MaskFormer", https://aurion.semai.id/models/meta-maskformer/, records of October 2026.