Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · facebook

mask2former-swin-tiny-coco-panoptic

mask2former-swin-tiny-coco-panoptic is a 47.46M-parameter Mask2Former model from facebook. Its card documents COCO panoptic segmentation with a Swin backbone.

Publisher
facebook
Task
image-segmentation
Model type
mask2former
License
other
Library
transformers
Publication status
Approved for indexing

Model overview

mask2former-swin-tiny-coco-panoptic is published by facebook as an image-segmentation model. The captured configuration identifies Mask2FormerForUniversalSegmentation with about 47.46M parameters. According to the model card, it is the tiny Swin-backbone version for COCO panoptic segmentation.

Recorded capabilities

COCO panoptic checkpoint

According to the model card, this is a Mask2Former model trained on COCO panoptic segmentation with a tiny Swin backbone.

47.46M Mask2Former configuration

The captured configuration identifies Mask2FormerForUniversalSegmentation with 47,464,210 parameters.

Unified segmentation design

The card describes Mask2Former as treating instance, semantic, and panoptic segmentation as mask-plus-label prediction with masked attention.

Use cases in the source record

  • Panoptic segmentation of COCO-style images using this specific tiny Swin checkpoint.
  • Vision experiments that compare unified instance, semantic, and panoptic segmentation behavior.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window or deployment-requirement value applies to this vision record beyond tagged deploy:azure.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • The card notes it was written by the Hugging Face team because the releasing team did not provide one.

Source and provenance

Source: facebook/mask2former-swin-tiny-coco-panoptic

Captured: Unknown. Processed: 2026-09-07T19:34:44.357496+00:00.

Mask2Former Mask2Former model trained on COCO panoptic segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository . Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Model description Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outp…

F001F002F003F004F005F006F007F008F009F010F011F012F013F014